diff options
Diffstat (limited to 'fs/btrfs/file.c')
-rw-r--r-- | fs/btrfs/file.c | 2659 |
1 files changed, 1658 insertions, 1001 deletions
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index a16da274c9aa..d01631d47806 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -16,6 +16,7 @@ #include <linux/btrfs.h> #include <linux/uio.h> #include <linux/iversion.h> +#include <linux/fsverity.h> #include "ctree.h" #include "disk-io.h" #include "transaction.h" @@ -27,6 +28,8 @@ #include "qgroup.h" #include "compression.h" #include "delalloc-space.h" +#include "reflink.h" +#include "subpage.h" static struct kmem_cache *btrfs_inode_defrag_cachep; /* @@ -47,11 +50,14 @@ struct inode_defrag { /* root objectid */ u64 root; - /* last offset we were able to defrag */ - u64 last_offset; - - /* if we've wrapped around back to zero once already */ - int cycled; + /* + * The extent size threshold for autodefrag. + * + * This value is different for compressed/non-compressed extents, + * thus needs to be passed from higher layer. + * (aka, inode_should_defrag()) + */ + u32 extent_thresh; }; static int __compare_inode_defrag(struct inode_defrag *defrag1, @@ -104,8 +110,8 @@ static int __btrfs_add_inode_defrag(struct btrfs_inode *inode, */ if (defrag->transid < entry->transid) entry->transid = defrag->transid; - if (defrag->last_offset > entry->last_offset) - entry->last_offset = defrag->last_offset; + entry->extent_thresh = min(defrag->extent_thresh, + entry->extent_thresh); return -EEXIST; } } @@ -131,7 +137,7 @@ static inline int __need_auto_defrag(struct btrfs_fs_info *fs_info) * enabled */ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, - struct btrfs_inode *inode) + struct btrfs_inode *inode, u32 extent_thresh) { struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; @@ -157,6 +163,7 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, defrag->ino = btrfs_ino(inode); defrag->transid = transid; defrag->root = root->root_key.objectid; + defrag->extent_thresh = extent_thresh; spin_lock(&fs_info->defrag_inodes_lock); if (!test_bit(BTRFS_INODE_IN_DEFRAG, &inode->runtime_flags)) { @@ -176,34 +183,6 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, } /* - * Requeue the defrag object. If there is a defrag object that points to - * the same inode in the tree, we will merge them together (by - * __btrfs_add_inode_defrag()) and free the one that we want to requeue. - */ -static void btrfs_requeue_inode_defrag(struct btrfs_inode *inode, - struct inode_defrag *defrag) -{ - struct btrfs_fs_info *fs_info = inode->root->fs_info; - int ret; - - if (!__need_auto_defrag(fs_info)) - goto out; - - /* - * Here we don't check the IN_DEFRAG flag, because we need merge - * them together. - */ - spin_lock(&fs_info->defrag_inodes_lock); - ret = __btrfs_add_inode_defrag(inode, defrag); - spin_unlock(&fs_info->defrag_inodes_lock); - if (ret) - goto out; - return; -out: - kmem_cache_free(btrfs_inode_defrag_cachep, defrag); -} - -/* * pick the defragable inode that we want, if it doesn't exist, we will get * the next one. */ @@ -274,70 +253,55 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info, { struct btrfs_root *inode_root; struct inode *inode; - struct btrfs_key key; struct btrfs_ioctl_defrag_range_args range; - int num_defrag; - int index; - int ret; - - /* get the inode */ - key.objectid = defrag->root; - key.type = BTRFS_ROOT_ITEM_KEY; - key.offset = (u64)-1; + int ret = 0; + u64 cur = 0; - index = srcu_read_lock(&fs_info->subvol_srcu); +again: + if (test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state)) + goto cleanup; + if (!__need_auto_defrag(fs_info)) + goto cleanup; - inode_root = btrfs_read_fs_root_no_name(fs_info, &key); + /* get the inode */ + inode_root = btrfs_get_fs_root(fs_info, defrag->root, true); if (IS_ERR(inode_root)) { ret = PTR_ERR(inode_root); goto cleanup; } - key.objectid = defrag->ino; - key.type = BTRFS_INODE_ITEM_KEY; - key.offset = 0; - inode = btrfs_iget(fs_info->sb, &key, inode_root); + inode = btrfs_iget(fs_info->sb, defrag->ino, inode_root); + btrfs_put_root(inode_root); if (IS_ERR(inode)) { ret = PTR_ERR(inode); goto cleanup; } - srcu_read_unlock(&fs_info->subvol_srcu, index); + + if (cur >= i_size_read(inode)) { + iput(inode); + goto cleanup; + } /* do a chunk of defrag */ clear_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags); memset(&range, 0, sizeof(range)); range.len = (u64)-1; - range.start = defrag->last_offset; + range.start = cur; + range.extent_thresh = defrag->extent_thresh; sb_start_write(fs_info->sb); - num_defrag = btrfs_defrag_file(inode, NULL, &range, defrag->transid, + ret = btrfs_defrag_file(inode, NULL, &range, defrag->transid, BTRFS_DEFRAG_BATCH); sb_end_write(fs_info->sb); - /* - * if we filled the whole defrag batch, there - * must be more work to do. Queue this defrag - * again - */ - if (num_defrag == BTRFS_DEFRAG_BATCH) { - defrag->last_offset = range.start; - btrfs_requeue_inode_defrag(BTRFS_I(inode), defrag); - } else if (defrag->last_offset && !defrag->cycled) { - /* - * we didn't fill our defrag batch, but - * we didn't start at zero. Make sure we loop - * around to the start of the file. - */ - defrag->last_offset = 0; - defrag->cycled = 1; - btrfs_requeue_inode_defrag(BTRFS_I(inode), defrag); - } else { - kmem_cache_free(btrfs_inode_defrag_cachep, defrag); - } - iput(inode); - return 0; + + if (ret < 0) + goto cleanup; + + cur = max(cur + fs_info->sectorsize, range.start); + goto again; + cleanup: - srcu_read_unlock(&fs_info->subvol_srcu, index); kmem_cache_free(btrfs_inode_defrag_cachep, defrag); return ret; } @@ -409,7 +373,7 @@ static noinline int btrfs_copy_from_user(loff_t pos, size_t write_bytes, /* * Copy data from userspace to the current page */ - copied = iov_iter_copy_from_user_atomic(page, i, offset, count); + copied = copy_page_from_iter_atomic(page, offset, count, i); /* Flush processor's dcache for this page */ flush_dcache_page(page); @@ -423,20 +387,19 @@ static noinline int btrfs_copy_from_user(loff_t pos, size_t write_bytes, * The rest of the btrfs_file_write code will fall * back to page at a time copies after we return 0. */ - if (!PageUptodate(page) && copied < count) - copied = 0; + if (unlikely(copied < count)) { + if (!PageUptodate(page)) { + iov_iter_revert(i, copied); + copied = 0; + } + if (!copied) + break; + } - iov_iter_advance(i, copied); write_bytes -= copied; total_copied += copied; - - /* Return to btrfs_file_write_iter to fault page */ - if (unlikely(copied == 0)) - break; - - if (copied < PAGE_SIZE - offset) { - offset += copied; - } else { + offset += copied; + if (offset == PAGE_SIZE) { pg++; offset = 0; } @@ -447,9 +410,15 @@ static noinline int btrfs_copy_from_user(loff_t pos, size_t write_bytes, /* * unlocks pages after btrfs_file_write is done with them */ -static void btrfs_drop_pages(struct page **pages, size_t num_pages) +static void btrfs_drop_pages(struct btrfs_fs_info *fs_info, + struct page **pages, size_t num_pages, + u64 pos, u64 copied) { size_t i; + u64 block_start = round_down(pos, fs_info->sectorsize); + u64 block_len = round_up(pos + copied, fs_info->sectorsize) - block_start; + + ASSERT(block_len <= U32_MAX); for (i = 0; i < num_pages; i++) { /* page checked is some magic around finding pages that * have been modified without going through btrfs_set_page_dirty @@ -457,77 +426,44 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages) * accessed as prepare_pages should have marked them accessed * in prepare_pages via find_or_create_page() */ - ClearPageChecked(pages[i]); + btrfs_page_clamp_clear_checked(fs_info, pages[i], block_start, + block_len); unlock_page(pages[i]); put_page(pages[i]); } } -static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode, - const u64 start, - const u64 len, - struct extent_state **cached_state) -{ - u64 search_start = start; - const u64 end = start + len - 1; - - while (search_start < end) { - const u64 search_len = end - search_start + 1; - struct extent_map *em; - u64 em_len; - int ret = 0; - - em = btrfs_get_extent(inode, NULL, 0, search_start, search_len); - if (IS_ERR(em)) - return PTR_ERR(em); - - if (em->block_start != EXTENT_MAP_HOLE) - goto next; - - em_len = em->len; - if (em->start < search_start) - em_len -= search_start - em->start; - if (em_len > search_len) - em_len = search_len; - - ret = set_extent_bit(&inode->io_tree, search_start, - search_start + em_len - 1, - EXTENT_DELALLOC_NEW, - NULL, cached_state, GFP_NOFS); -next: - search_start = extent_map_end(em); - free_extent_map(em); - if (ret) - return ret; - } - return 0; -} - /* - * after copy_from_user, pages need to be dirtied and we need to make - * sure holes are created between the current EOF and the start of - * any next extents (if required). - * - * this also makes the decision about creating an inline extent vs - * doing real data extents, marking pages dirty and delalloc as required. + * After btrfs_copy_from_user(), update the following things for delalloc: + * - Mark newly dirtied pages as DELALLOC in the io tree. + * Used to advise which range is to be written back. + * - Mark modified pages as Uptodate/Dirty and not needing COW fixup + * - Update inode size for past EOF write */ -int btrfs_dirty_pages(struct inode *inode, struct page **pages, +int btrfs_dirty_pages(struct btrfs_inode *inode, struct page **pages, size_t num_pages, loff_t pos, size_t write_bytes, - struct extent_state **cached) + struct extent_state **cached, bool noreserve) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode->root->fs_info; int err = 0; int i; u64 num_bytes; u64 start_pos; u64 end_of_last_block; u64 end_pos = pos + write_bytes; - loff_t isize = i_size_read(inode); + loff_t isize = i_size_read(&inode->vfs_inode); unsigned int extra_bits = 0; - start_pos = pos & ~((u64) fs_info->sectorsize - 1); + if (write_bytes == 0) + return 0; + + if (noreserve) + extra_bits |= EXTENT_NORESERVE; + + start_pos = round_down(pos, fs_info->sectorsize); num_bytes = round_up(write_bytes + pos - start_pos, fs_info->sectorsize); + ASSERT(num_bytes <= U32_MAX); end_of_last_block = start_pos + num_bytes - 1; @@ -535,27 +471,9 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages, * The pages may have already been dirty, clear out old accounting so * we can set things up properly */ - clear_extent_bit(&BTRFS_I(inode)->io_tree, start_pos, end_of_last_block, + clear_extent_bit(&inode->io_tree, start_pos, end_of_last_block, EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, - 0, 0, cached); - - if (!btrfs_is_free_space_inode(BTRFS_I(inode))) { - if (start_pos >= isize && - !(BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC)) { - /* - * There can't be any extents following eof in this case - * so just set the delalloc new bit for the range - * directly. - */ - extra_bits |= EXTENT_DELALLOC_NEW; - } else { - err = btrfs_find_new_delalloc_bytes(BTRFS_I(inode), - start_pos, - num_bytes, cached); - if (err) - return err; - } - } + cached); err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block, extra_bits, cached); @@ -564,9 +482,10 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages, for (i = 0; i < num_pages; i++) { struct page *p = pages[i]; - SetPageUptodate(p); - ClearPageChecked(p); - set_page_dirty(p); + + btrfs_page_clamp_set_uptodate(fs_info, p, start_pos, num_bytes); + btrfs_page_clamp_clear_checked(fs_info, p, start_pos, num_bytes); + btrfs_page_clamp_set_dirty(fs_info, p, start_pos, num_bytes); } /* @@ -575,164 +494,11 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages, * at this time. */ if (end_pos > isize) - i_size_write(inode, end_pos); + i_size_write(&inode->vfs_inode, end_pos); return 0; } /* - * this drops all the extents in the cache that intersect the range - * [start, end]. Existing extents are split as required. - */ -void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end, - int skip_pinned) -{ - struct extent_map *em; - struct extent_map *split = NULL; - struct extent_map *split2 = NULL; - struct extent_map_tree *em_tree = &inode->extent_tree; - u64 len = end - start + 1; - u64 gen; - int ret; - int testend = 1; - unsigned long flags; - int compressed = 0; - bool modified; - - WARN_ON(end < start); - if (end == (u64)-1) { - len = (u64)-1; - testend = 0; - } - while (1) { - int no_splits = 0; - - modified = false; - if (!split) - split = alloc_extent_map(); - if (!split2) - split2 = alloc_extent_map(); - if (!split || !split2) - no_splits = 1; - - write_lock(&em_tree->lock); - em = lookup_extent_mapping(em_tree, start, len); - if (!em) { - write_unlock(&em_tree->lock); - break; - } - flags = em->flags; - gen = em->generation; - if (skip_pinned && test_bit(EXTENT_FLAG_PINNED, &em->flags)) { - if (testend && em->start + em->len >= start + len) { - free_extent_map(em); - write_unlock(&em_tree->lock); - break; - } - start = em->start + em->len; - if (testend) - len = start + len - (em->start + em->len); - free_extent_map(em); - write_unlock(&em_tree->lock); - continue; - } - compressed = test_bit(EXTENT_FLAG_COMPRESSED, &em->flags); - clear_bit(EXTENT_FLAG_PINNED, &em->flags); - clear_bit(EXTENT_FLAG_LOGGING, &flags); - modified = !list_empty(&em->list); - if (no_splits) - goto next; - - if (em->start < start) { - split->start = em->start; - split->len = start - em->start; - - if (em->block_start < EXTENT_MAP_LAST_BYTE) { - split->orig_start = em->orig_start; - split->block_start = em->block_start; - - if (compressed) - split->block_len = em->block_len; - else - split->block_len = split->len; - split->orig_block_len = max(split->block_len, - em->orig_block_len); - split->ram_bytes = em->ram_bytes; - } else { - split->orig_start = split->start; - split->block_len = 0; - split->block_start = em->block_start; - split->orig_block_len = 0; - split->ram_bytes = split->len; - } - - split->generation = gen; - split->flags = flags; - split->compress_type = em->compress_type; - replace_extent_mapping(em_tree, em, split, modified); - free_extent_map(split); - split = split2; - split2 = NULL; - } - if (testend && em->start + em->len > start + len) { - u64 diff = start + len - em->start; - - split->start = start + len; - split->len = em->start + em->len - (start + len); - split->flags = flags; - split->compress_type = em->compress_type; - split->generation = gen; - - if (em->block_start < EXTENT_MAP_LAST_BYTE) { - split->orig_block_len = max(em->block_len, - em->orig_block_len); - - split->ram_bytes = em->ram_bytes; - if (compressed) { - split->block_len = em->block_len; - split->block_start = em->block_start; - split->orig_start = em->orig_start; - } else { - split->block_len = split->len; - split->block_start = em->block_start - + diff; - split->orig_start = em->orig_start; - } - } else { - split->ram_bytes = split->len; - split->orig_start = split->start; - split->block_len = 0; - split->block_start = em->block_start; - split->orig_block_len = 0; - } - - if (extent_map_in_tree(em)) { - replace_extent_mapping(em_tree, em, split, - modified); - } else { - ret = add_extent_mapping(em_tree, split, - modified); - ASSERT(ret == 0); /* Logic error */ - } - free_extent_map(split); - split = NULL; - } -next: - if (extent_map_in_tree(em)) - remove_extent_mapping(em_tree, em); - write_unlock(&em_tree->lock); - - /* once for us */ - free_extent_map(em); - /* once for the tree*/ - free_extent_map(em); - } - if (split) - free_extent_map(split); - if (split2) - free_extent_map(split2); -} - -/* * this is very complex, but the basic idea is to drop all extents * in the range start - end. hint_block is filled in with a block number * that would be a good hint to the block allocator for this file. @@ -740,14 +506,16 @@ next: * If an extent intersects the range but is not entirely inside the range * it is either truncated or split. Anything entirely inside the range * is deleted from the tree. + * + * Note: the VFS' inode number of bytes is not updated, it's up to the caller + * to deal with that. We set the field 'bytes_found' of the arguments structure + * with the number of allocated bytes found in the target range, so that the + * caller can update the inode's number of bytes in an atomic way when + * replacing extents in a range to avoid races with stat(2). */ -int __btrfs_drop_extents(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct inode *inode, - struct btrfs_path *path, u64 start, u64 end, - u64 *drop_end, int drop_cache, - int replace_extent, - u32 extent_item_size, - int *key_inserted) +int btrfs_drop_extents(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct btrfs_inode *inode, + struct btrfs_drop_extents_args *args) { struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *leaf; @@ -755,13 +523,13 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans, struct btrfs_ref ref = { 0 }; struct btrfs_key key; struct btrfs_key new_key; - u64 ino = btrfs_ino(BTRFS_I(inode)); - u64 search_start = start; + u64 ino = btrfs_ino(inode); + u64 search_start = args->start; u64 disk_bytenr = 0; u64 num_bytes = 0; u64 extent_offset = 0; u64 extent_end = 0; - u64 last_end = start; + u64 last_end = args->start; int del_nr = 0; int del_slot = 0; int extent_type; @@ -770,23 +538,36 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans, int modify_tree = -1; int update_refs; int found = 0; - int leafs_visited = 0; + struct btrfs_path *path = args->path; - if (drop_cache) - btrfs_drop_extent_cache(BTRFS_I(inode), start, end - 1, 0); + args->bytes_found = 0; + args->extent_inserted = false; - if (start >= BTRFS_I(inode)->disk_i_size && !replace_extent) + /* Must always have a path if ->replace_extent is true */ + ASSERT(!(args->replace_extent && !args->path)); + + if (!path) { + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; + goto out; + } + } + + if (args->drop_cache) + btrfs_drop_extent_map_range(inode, args->start, args->end - 1, false); + + if (args->start >= inode->disk_i_size && !args->replace_extent) modify_tree = 0; - update_refs = (test_bit(BTRFS_ROOT_REF_COWS, &root->state) || - root == fs_info->tree_root); + update_refs = (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID); while (1) { recow = 0; ret = btrfs_lookup_file_extent(trans, root, path, ino, search_start, modify_tree); if (ret < 0) break; - if (ret > 0 && path->slots[0] > 0 && search_start == start) { + if (ret > 0 && path->slots[0] > 0 && search_start == args->start) { leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, path->slots[0] - 1); if (key.objectid == ino && @@ -794,7 +575,6 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans, path->slots[0]--; } ret = 0; - leafs_visited++; next_slot: leaf = path->nodes[0]; if (path->slots[0] >= btrfs_header_nritems(leaf)) { @@ -806,7 +586,6 @@ next_slot: ret = 0; break; } - leafs_visited++; leaf = path->nodes[0]; recow = 1; } @@ -821,7 +600,7 @@ next_slot: path->slots[0]++; goto next_slot; } - if (key.type > BTRFS_EXTENT_DATA_KEY || key.offset >= end) + if (key.type > BTRFS_EXTENT_DATA_KEY || key.offset >= args->end) break; fi = btrfs_item_ptr(leaf, path->slots[0], @@ -863,7 +642,7 @@ next_slot: } found = 1; - search_start = max(key.offset, start); + search_start = max(key.offset, args->start); if (recow || !modify_tree) { modify_tree = -1; btrfs_release_path(path); @@ -874,7 +653,7 @@ next_slot: * | - range to drop - | * | -------- extent -------- | */ - if (start > key.offset && end < extent_end) { + if (args->start > key.offset && args->end < extent_end) { BUG_ON(del_nr > 0); if (extent_type == BTRFS_FILE_EXTENT_INLINE) { ret = -EOPNOTSUPP; @@ -882,7 +661,7 @@ next_slot: } memcpy(&new_key, &key, sizeof(new_key)); - new_key.offset = start; + new_key.offset = args->start; ret = btrfs_duplicate_item(trans, root, path, &new_key); if (ret == -EAGAIN) { @@ -896,15 +675,15 @@ next_slot: fi = btrfs_item_ptr(leaf, path->slots[0] - 1, struct btrfs_file_extent_item); btrfs_set_file_extent_num_bytes(leaf, fi, - start - key.offset); + args->start - key.offset); fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); - extent_offset += start - key.offset; + extent_offset += args->start - key.offset; btrfs_set_file_extent_offset(leaf, fi, extent_offset); btrfs_set_file_extent_num_bytes(leaf, fi, - extent_end - start); + extent_end - args->start); btrfs_mark_buffer_dirty(leaf); if (update_refs && disk_bytenr > 0) { @@ -914,11 +693,12 @@ next_slot: btrfs_init_data_ref(&ref, root->root_key.objectid, new_key.objectid, - start - extent_offset); + args->start - extent_offset, + 0, false); ret = btrfs_inc_extent_ref(trans, &ref); BUG_ON(ret); /* -ENOMEM */ } - key.offset = start; + key.offset = args->start; } /* * From here on out we will have actually dropped something, so @@ -930,23 +710,23 @@ next_slot: * | ---- range to drop ----- | * | -------- extent -------- | */ - if (start <= key.offset && end < extent_end) { + if (args->start <= key.offset && args->end < extent_end) { if (extent_type == BTRFS_FILE_EXTENT_INLINE) { ret = -EOPNOTSUPP; break; } memcpy(&new_key, &key, sizeof(new_key)); - new_key.offset = end; + new_key.offset = args->end; btrfs_set_item_key_safe(fs_info, path, &new_key); - extent_offset += end - key.offset; + extent_offset += args->end - key.offset; btrfs_set_file_extent_offset(leaf, fi, extent_offset); btrfs_set_file_extent_num_bytes(leaf, fi, - extent_end - end); + extent_end - args->end); btrfs_mark_buffer_dirty(leaf); if (update_refs && disk_bytenr > 0) - inode_sub_bytes(inode, end - key.offset); + args->bytes_found += args->end - key.offset; break; } @@ -955,7 +735,7 @@ next_slot: * | ---- range to drop ----- | * | -------- extent -------- | */ - if (start > key.offset && end >= extent_end) { + if (args->start > key.offset && args->end >= extent_end) { BUG_ON(del_nr > 0); if (extent_type == BTRFS_FILE_EXTENT_INLINE) { ret = -EOPNOTSUPP; @@ -963,11 +743,11 @@ next_slot: } btrfs_set_file_extent_num_bytes(leaf, fi, - start - key.offset); + args->start - key.offset); btrfs_mark_buffer_dirty(leaf); if (update_refs && disk_bytenr > 0) - inode_sub_bytes(inode, extent_end - start); - if (end == extent_end) + args->bytes_found += extent_end - args->start; + if (args->end == extent_end) break; path->slots[0]++; @@ -978,7 +758,7 @@ next_slot: * | ---- range to drop ----- | * | ------ extent ------ | */ - if (start <= key.offset && end >= extent_end) { + if (args->start <= key.offset && args->end >= extent_end) { delete_extent_item: if (del_nr == 0) { del_slot = path->slots[0]; @@ -990,8 +770,7 @@ delete_extent_item: if (update_refs && extent_type == BTRFS_FILE_EXTENT_INLINE) { - inode_sub_bytes(inode, - extent_end - key.offset); + args->bytes_found += extent_end - key.offset; extent_end = ALIGN(extent_end, fs_info->sectorsize); } else if (update_refs && disk_bytenr > 0) { @@ -1001,14 +780,14 @@ delete_extent_item: btrfs_init_data_ref(&ref, root->root_key.objectid, key.objectid, - key.offset - extent_offset); + key.offset - extent_offset, 0, + false); ret = btrfs_free_extent(trans, &ref); BUG_ON(ret); /* -ENOMEM */ - inode_sub_bytes(inode, - extent_end - key.offset); + args->bytes_found += extent_end - key.offset; } - if (end == extent_end) + if (args->end == extent_end) break; if (path->slots[0] + 1 < btrfs_header_nritems(leaf)) { @@ -1038,7 +817,7 @@ delete_extent_item: * Set path->slots[0] to first slot, so that after the delete * if items are move off from our leaf to its immediate left or * right neighbor leafs, we end up with a correct and adjusted - * path->slots[0] for our insertion (if replace_extent != 0). + * path->slots[0] for our insertion (if args->replace_extent). */ path->slots[0] = del_slot; ret = btrfs_del_items(trans, root, path, del_slot, del_nr); @@ -1052,15 +831,14 @@ delete_extent_item: * which case it unlocked our path, so check path->locks[0] matches a * write lock. */ - if (!ret && replace_extent && leafs_visited == 1 && - (path->locks[0] == BTRFS_WRITE_LOCK_BLOCKING || - path->locks[0] == BTRFS_WRITE_LOCK) && + if (!ret && args->replace_extent && + path->locks[0] == BTRFS_WRITE_LOCK && btrfs_leaf_free_space(leaf) >= - sizeof(struct btrfs_item) + extent_item_size) { + sizeof(struct btrfs_item) + args->extent_item_size) { key.objectid = ino; key.type = BTRFS_EXTENT_DATA_KEY; - key.offset = start; + key.offset = args->start; if (!del_nr && path->slots[0] < btrfs_header_nritems(leaf)) { struct btrfs_key slot_key; @@ -1068,34 +846,17 @@ delete_extent_item: if (btrfs_comp_cpu_keys(&key, &slot_key) > 0) path->slots[0]++; } - setup_items_for_insert(root, path, &key, - &extent_item_size, - extent_item_size, - sizeof(struct btrfs_item) + - extent_item_size, 1); - *key_inserted = 1; + btrfs_setup_item_for_insert(root, path, &key, args->extent_item_size); + args->extent_inserted = true; } - if (!replace_extent || !(*key_inserted)) + if (!args->path) + btrfs_free_path(path); + else if (!args->extent_inserted) btrfs_release_path(path); - if (drop_end) - *drop_end = found ? min(end, last_end) : end; - return ret; -} - -int btrfs_drop_extents(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct inode *inode, u64 start, - u64 end, int drop_cache) -{ - struct btrfs_path *path; - int ret; +out: + args->drop_end = found ? min(args->end, last_end) : args->end; - path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; - ret = __btrfs_drop_extents(trans, root, inode, path, start, end, NULL, - drop_cache, 0, 0, NULL); - btrfs_free_path(path); return ret; } @@ -1160,7 +921,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans, int del_nr = 0; int del_slot = 0; int recow; - int ret; + int ret = 0; u64 ino = btrfs_ino(inode); path = btrfs_alloc_path(); @@ -1296,7 +1057,7 @@ again: btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, bytenr, num_bytes, 0); btrfs_init_data_ref(&ref, root->root_key.objectid, ino, - orig_offset); + orig_offset, 0, false); ret = btrfs_inc_extent_ref(trans, &ref); if (ret) { btrfs_abort_transaction(trans, ret); @@ -1321,7 +1082,8 @@ again: other_end = 0; btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, bytenr, num_bytes, 0); - btrfs_init_data_ref(&ref, root->root_key.objectid, ino, orig_offset); + btrfs_init_data_ref(&ref, root->root_key.objectid, ino, orig_offset, + 0, false); if (extent_mergeable(leaf, path->slots[0] + 1, ino, bytenr, orig_offset, &other_start, &other_end)) { @@ -1381,7 +1143,7 @@ again: } out: btrfs_free_path(path); - return 0; + return ret; } /* @@ -1392,11 +1154,12 @@ static int prepare_uptodate_page(struct inode *inode, struct page *page, u64 pos, bool force_uptodate) { + struct folio *folio = page_folio(page); int ret = 0; if (((pos & (PAGE_SIZE - 1)) || force_uptodate) && !PageUptodate(page)) { - ret = btrfs_readpage(NULL, page); + ret = btrfs_read_folio(NULL, folio); if (ret) return ret; lock_page(page); @@ -1404,7 +1167,18 @@ static int prepare_uptodate_page(struct inode *inode, unlock_page(page); return -EIO; } - if (page->mapping != inode->i_mapping) { + + /* + * Since btrfs_read_folio() will unlock the folio before it + * returns, there is a window where btrfs_release_folio() can be + * called to release the page. Here we check both inode + * mapping and PagePrivate() to make sure the page was not + * released. + * + * The private flag check is essential for subpage as we need + * to store extra bitmap using page->private. + */ + if (page->mapping != inode->i_mapping || !PagePrivate(page)) { unlock_page(page); return -EAGAIN; } @@ -1412,26 +1186,60 @@ static int prepare_uptodate_page(struct inode *inode, return 0; } +static unsigned int get_prepare_fgp_flags(bool nowait) +{ + unsigned int fgp_flags = FGP_LOCK | FGP_ACCESSED | FGP_CREAT; + + if (nowait) + fgp_flags |= FGP_NOWAIT; + + return fgp_flags; +} + +static gfp_t get_prepare_gfp_flags(struct inode *inode, bool nowait) +{ + gfp_t gfp; + + gfp = btrfs_alloc_write_mask(inode->i_mapping); + if (nowait) { + gfp &= ~__GFP_DIRECT_RECLAIM; + gfp |= GFP_NOWAIT; + } + + return gfp; +} + /* * this just gets pages into the page cache and locks them down. */ static noinline int prepare_pages(struct inode *inode, struct page **pages, size_t num_pages, loff_t pos, - size_t write_bytes, bool force_uptodate) + size_t write_bytes, bool force_uptodate, + bool nowait) { int i; unsigned long index = pos >> PAGE_SHIFT; - gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping); + gfp_t mask = get_prepare_gfp_flags(inode, nowait); + unsigned int fgp_flags = get_prepare_fgp_flags(nowait); int err = 0; int faili; for (i = 0; i < num_pages; i++) { again: - pages[i] = find_or_create_page(inode->i_mapping, index + i, - mask | __GFP_WRITE); + pages[i] = pagecache_get_page(inode->i_mapping, index + i, + fgp_flags, mask | __GFP_WRITE); if (!pages[i]) { faili = i - 1; - err = -ENOMEM; + if (nowait) + err = -EAGAIN; + else + err = -ENOMEM; + goto fail; + } + + err = set_page_extent_mapped(pages[i]); + if (err < 0) { + faili = i; goto fail; } @@ -1443,7 +1251,7 @@ again: pos + write_bytes, false); if (err) { put_page(pages[i]); - if (err == -EAGAIN) { + if (!nowait && err == -EAGAIN) { err = 0; goto again; } @@ -1478,7 +1286,7 @@ static noinline int lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages, size_t num_pages, loff_t pos, size_t write_bytes, - u64 *lockstart, u64 *lockend, + u64 *lockstart, u64 *lockend, bool nowait, struct extent_state **cached_state) { struct btrfs_fs_info *fs_info = inode->root->fs_info; @@ -1488,28 +1296,37 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages, int ret = 0; start_pos = round_down(pos, fs_info->sectorsize); - last_pos = start_pos - + round_up(pos + write_bytes - start_pos, - fs_info->sectorsize) - 1; + last_pos = round_up(pos + write_bytes, fs_info->sectorsize) - 1; if (start_pos < inode->vfs_inode.i_size) { struct btrfs_ordered_extent *ordered; - lock_extent_bits(&inode->io_tree, start_pos, last_pos, - cached_state); + if (nowait) { + if (!try_lock_extent(&inode->io_tree, start_pos, last_pos)) { + for (i = 0; i < num_pages; i++) { + unlock_page(pages[i]); + put_page(pages[i]); + pages[i] = NULL; + } + + return -EAGAIN; + } + } else { + lock_extent(&inode->io_tree, start_pos, last_pos, cached_state); + } + ordered = btrfs_lookup_ordered_range(inode, start_pos, last_pos - start_pos + 1); if (ordered && ordered->file_offset + ordered->num_bytes > start_pos && ordered->file_offset <= last_pos) { - unlock_extent_cached(&inode->io_tree, start_pos, - last_pos, cached_state); + unlock_extent(&inode->io_tree, start_pos, last_pos, + cached_state); for (i = 0; i < num_pages; i++) { unlock_page(pages[i]); put_page(pages[i]); } - btrfs_start_ordered_extent(&inode->vfs_inode, - ordered, 1); + btrfs_start_ordered_extent(ordered, 1); btrfs_put_ordered_extent(ordered); return -EAGAIN; } @@ -1522,29 +1339,36 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages, } /* - * It's possible the pages are dirty right now, but we don't want - * to clean them yet because copy_from_user may catch a page fault - * and we might have to fall back to one page at a time. If that - * happens, we'll unlock these pages and we'd have a window where - * reclaim could sneak in and drop the once-dirty page on the floor - * without writing it. - * - * We have the pages locked and the extent range locked, so there's - * no way someone can start IO on any dirty pages in this range. - * - * We'll call btrfs_dirty_pages() later on, and that will flip around - * delalloc bits and dirty the pages as required. + * We should be called after prepare_pages() which should have locked + * all pages in the range. */ - for (i = 0; i < num_pages; i++) { - set_page_extent_mapped(pages[i]); + for (i = 0; i < num_pages; i++) WARN_ON(!PageLocked(pages[i])); - } return ret; } -static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos, - size_t *write_bytes) +/* + * Check if we can do nocow write into the range [@pos, @pos + @write_bytes) + * + * @pos: File offset. + * @write_bytes: The length to write, will be updated to the nocow writeable + * range. + * + * This function will flush ordered extents in the range to ensure proper + * nocow checks. + * + * Return: + * > 0 If we can nocow, and updates @write_bytes. + * 0 If we can't do a nocow write. + * -EAGAIN If we can't do a nocow write because snapshoting of the inode's + * root is in progress. + * < 0 If an error happened. + * + * NOTE: Callers need to call btrfs_check_nocow_unlock() if we return > 0. + */ +int btrfs_check_nocow_lock(struct btrfs_inode *inode, loff_t pos, + size_t *write_bytes, bool nowait) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_root *root = inode->root; @@ -1552,41 +1376,117 @@ static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos, u64 num_bytes; int ret; - ret = btrfs_start_write_no_snapshotting(root); - if (!ret) + if (!(inode->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC))) + return 0; + + if (!btrfs_drew_try_write_lock(&root->snapshot_lock)) return -EAGAIN; lockstart = round_down(pos, fs_info->sectorsize); lockend = round_up(pos + *write_bytes, fs_info->sectorsize) - 1; - - btrfs_lock_and_flush_ordered_range(&inode->io_tree, inode, lockstart, - lockend, NULL); - num_bytes = lockend - lockstart + 1; - ret = can_nocow_extent(&inode->vfs_inode, lockstart, &num_bytes, - NULL, NULL, NULL); - if (ret <= 0) { - ret = 0; - btrfs_end_write_no_snapshotting(root); + + if (nowait) { + if (!btrfs_try_lock_ordered_range(inode, lockstart, lockend)) { + btrfs_drew_write_unlock(&root->snapshot_lock); + return -EAGAIN; + } } else { + btrfs_lock_and_flush_ordered_range(inode, lockstart, lockend, NULL); + } + ret = can_nocow_extent(&inode->vfs_inode, lockstart, &num_bytes, + NULL, NULL, NULL, nowait, false); + if (ret <= 0) + btrfs_drew_write_unlock(&root->snapshot_lock); + else *write_bytes = min_t(size_t, *write_bytes , num_bytes - pos + lockstart); - } - - unlock_extent(&inode->io_tree, lockstart, lockend); + unlock_extent(&inode->io_tree, lockstart, lockend, NULL); return ret; } +void btrfs_check_nocow_unlock(struct btrfs_inode *inode) +{ + btrfs_drew_write_unlock(&inode->root->snapshot_lock); +} + +static void update_time_for_write(struct inode *inode) +{ + struct timespec64 now; + + if (IS_NOCMTIME(inode)) + return; + + now = current_time(inode); + if (!timespec64_equal(&inode->i_mtime, &now)) + inode->i_mtime = now; + + if (!timespec64_equal(&inode->i_ctime, &now)) + inode->i_ctime = now; + + if (IS_I_VERSION(inode)) + inode_inc_iversion(inode); +} + +static int btrfs_write_check(struct kiocb *iocb, struct iov_iter *from, + size_t count) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file_inode(file); + struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + loff_t pos = iocb->ki_pos; + int ret; + loff_t oldsize; + loff_t start_pos; + + /* + * Quickly bail out on NOWAIT writes if we don't have the nodatacow or + * prealloc flags, as without those flags we always have to COW. We will + * later check if we can really COW into the target range (using + * can_nocow_extent() at btrfs_get_blocks_direct_write()). + */ + if ((iocb->ki_flags & IOCB_NOWAIT) && + !(BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC))) + return -EAGAIN; + + current->backing_dev_info = inode_to_bdi(inode); + ret = file_remove_privs(file); + if (ret) + return ret; + + /* + * We reserve space for updating the inode when we reserve space for the + * extent we are going to write, so we will enospc out there. We don't + * need to start yet another transaction to update the inode as we will + * update the inode when we finish writing whatever data we write. + */ + update_time_for_write(inode); + + start_pos = round_down(pos, fs_info->sectorsize); + oldsize = i_size_read(inode); + if (start_pos > oldsize) { + /* Expand hole size to cover write data, preventing empty gap */ + loff_t end_pos = round_up(pos + count, fs_info->sectorsize); + + ret = btrfs_cont_expand(BTRFS_I(inode), oldsize, end_pos); + if (ret) { + current->backing_dev_info = NULL; + return ret; + } + } + + return 0; +} + static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, struct iov_iter *i) { struct file *file = iocb->ki_filp; - loff_t pos = iocb->ki_pos; + loff_t pos; struct inode *inode = file_inode(file); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; struct page **pages = NULL; struct extent_changeset *data_reserved = NULL; u64 release_bytes = 0; @@ -1594,17 +1494,39 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, u64 lockend; size_t num_written = 0; int nrptrs; - int ret = 0; + ssize_t ret; bool only_release_metadata = false; bool force_page_uptodate = false; + loff_t old_isize = i_size_read(inode); + unsigned int ilock_flags = 0; + const bool nowait = (iocb->ki_flags & IOCB_NOWAIT); + unsigned int bdp_flags = (nowait ? BDP_ASYNC : 0); + + if (nowait) + ilock_flags |= BTRFS_ILOCK_TRY; + + ret = btrfs_inode_lock(inode, ilock_flags); + if (ret < 0) + return ret; + + ret = generic_write_checks(iocb, i); + if (ret <= 0) + goto out; + ret = btrfs_write_check(iocb, i, ret); + if (ret < 0) + goto out; + + pos = iocb->ki_pos; nrptrs = min(DIV_ROUND_UP(iov_iter_count(i), PAGE_SIZE), PAGE_SIZE / (sizeof(struct page *))); nrptrs = min(nrptrs, current->nr_dirtied_pause - current->nr_dirtied); nrptrs = max(nrptrs, 8); pages = kmalloc_array(nrptrs, sizeof(struct page *), GFP_KERNEL); - if (!pages) - return -ENOMEM; + if (!pages) { + ret = -ENOMEM; + goto out; + } while (iov_iter_count(i) > 0) { struct extent_state *cached_state = NULL; @@ -1613,8 +1535,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, size_t write_bytes = min(iov_iter_count(i), nrptrs * (size_t)PAGE_SIZE - offset); - size_t num_pages = DIV_ROUND_UP(write_bytes + offset, - PAGE_SIZE); + size_t num_pages; size_t reserve_bytes; size_t dirty_pages; size_t copied; @@ -1622,72 +1543,82 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, size_t num_sectors; int extents_locked; - WARN_ON(num_pages > nrptrs); - /* * Fault pages before locking them in prepare_pages * to avoid recursive lock */ - if (unlikely(iov_iter_fault_in_readable(i, write_bytes))) { + if (unlikely(fault_in_iov_iter_readable(i, write_bytes))) { ret = -EFAULT; break; } only_release_metadata = false; sector_offset = pos & (fs_info->sectorsize - 1); - reserve_bytes = round_up(write_bytes + sector_offset, - fs_info->sectorsize); extent_changeset_release(data_reserved); - ret = btrfs_check_data_free_space(inode, &data_reserved, pos, - write_bytes); + ret = btrfs_check_data_free_space(BTRFS_I(inode), + &data_reserved, pos, + write_bytes, nowait); if (ret < 0) { - if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | - BTRFS_INODE_PREALLOC)) && - check_can_nocow(BTRFS_I(inode), pos, - &write_bytes) > 0) { - /* - * For nodata cow case, no need to reserve - * data space. - */ - only_release_metadata = true; - /* - * our prealloc extent may be smaller than - * write_bytes, so scale down. - */ - num_pages = DIV_ROUND_UP(write_bytes + offset, - PAGE_SIZE); - reserve_bytes = round_up(write_bytes + - sector_offset, - fs_info->sectorsize); - } else { + int can_nocow; + + if (nowait && (ret == -ENOSPC || ret == -EAGAIN)) { + ret = -EAGAIN; break; } + + /* + * If we don't have to COW at the offset, reserve + * metadata only. write_bytes may get smaller than + * requested here. + */ + can_nocow = btrfs_check_nocow_lock(BTRFS_I(inode), pos, + &write_bytes, nowait); + if (can_nocow < 0) + ret = can_nocow; + if (can_nocow > 0) + ret = 0; + if (ret) + break; + only_release_metadata = true; } + num_pages = DIV_ROUND_UP(write_bytes + offset, PAGE_SIZE); + WARN_ON(num_pages > nrptrs); + reserve_bytes = round_up(write_bytes + sector_offset, + fs_info->sectorsize); WARN_ON(reserve_bytes == 0); ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), - reserve_bytes); + reserve_bytes, + reserve_bytes, nowait); if (ret) { if (!only_release_metadata) - btrfs_free_reserved_data_space(inode, + btrfs_free_reserved_data_space(BTRFS_I(inode), data_reserved, pos, write_bytes); else - btrfs_end_write_no_snapshotting(root); + btrfs_check_nocow_unlock(BTRFS_I(inode)); + + if (nowait && ret == -ENOSPC) + ret = -EAGAIN; break; } release_bytes = reserve_bytes; again: + ret = balance_dirty_pages_ratelimited_flags(inode->i_mapping, bdp_flags); + if (ret) { + btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes); + break; + } + /* * This is going to setup the pages array with the number of * pages we want, so we don't really need to worry about the * contents of pages from loop to loop */ ret = prepare_pages(inode, pages, num_pages, - pos, write_bytes, - force_page_uptodate); + pos, write_bytes, force_page_uptodate, false); if (ret) { btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes); @@ -1697,10 +1628,11 @@ again: extents_locked = lock_and_cleanup_extent_if_need( BTRFS_I(inode), pages, num_pages, pos, write_bytes, &lockstart, - &lockend, &cached_state); + &lockend, nowait, &cached_state); if (extents_locked < 0) { - if (extents_locked == -EAGAIN) + if (!nowait && extents_locked == -EAGAIN) goto again; + btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes); ret = extents_locked; @@ -1733,8 +1665,7 @@ again: if (num_sectors > dirty_sectors) { /* release everything except the sectors we dirtied */ - release_bytes -= dirty_sectors << - fs_info->sb->s_blocksize_bits; + release_bytes -= dirty_sectors << fs_info->sectorsize_bits; if (only_release_metadata) { btrfs_delalloc_release_metadata(BTRFS_I(inode), release_bytes, true); @@ -1744,7 +1675,7 @@ again: __pos = round_down(pos, fs_info->sectorsize) + (dirty_pages << PAGE_SHIFT); - btrfs_delalloc_release_space(inode, + btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, __pos, release_bytes, true); } @@ -1753,9 +1684,9 @@ again: release_bytes = round_up(copied + sector_offset, fs_info->sectorsize); - if (copied > 0) - ret = btrfs_dirty_pages(inode, pages, dirty_pages, - pos, copied, &cached_state); + ret = btrfs_dirty_pages(BTRFS_I(inode), pages, + dirty_pages, pos, copied, + &cached_state, only_release_metadata); /* * If we have not locked the extent range, because the range's @@ -1765,40 +1696,25 @@ again: * possible cached extent state to avoid a memory leak. */ if (extents_locked) - unlock_extent_cached(&BTRFS_I(inode)->io_tree, - lockstart, lockend, &cached_state); + unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, + lockend, &cached_state); else free_extent_state(cached_state); btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes); if (ret) { - btrfs_drop_pages(pages, num_pages); + btrfs_drop_pages(fs_info, pages, num_pages, pos, copied); break; } release_bytes = 0; if (only_release_metadata) - btrfs_end_write_no_snapshotting(root); - - if (only_release_metadata && copied > 0) { - lockstart = round_down(pos, - fs_info->sectorsize); - lockend = round_up(pos + copied, - fs_info->sectorsize) - 1; - - set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, - lockend, EXTENT_NORESERVE, NULL, - NULL, GFP_NOFS); - } + btrfs_check_nocow_unlock(BTRFS_I(inode)); - btrfs_drop_pages(pages, num_pages); + btrfs_drop_pages(fs_info, pages, num_pages, pos, copied); cond_resched(); - balance_dirty_pages_ratelimited(inode->i_mapping); - if (dirty_pages < (fs_info->nodesize >> PAGE_SHIFT) + 1) - btrfs_btree_balance_dirty(fs_info); - pos += copied; num_written += copied; } @@ -1807,34 +1723,177 @@ again: if (release_bytes) { if (only_release_metadata) { - btrfs_end_write_no_snapshotting(root); + btrfs_check_nocow_unlock(BTRFS_I(inode)); btrfs_delalloc_release_metadata(BTRFS_I(inode), release_bytes, true); } else { - btrfs_delalloc_release_space(inode, data_reserved, + btrfs_delalloc_release_space(BTRFS_I(inode), + data_reserved, round_down(pos, fs_info->sectorsize), release_bytes, true); } } extent_changeset_free(data_reserved); + if (num_written > 0) { + pagecache_isize_extended(inode, old_isize, iocb->ki_pos); + iocb->ki_pos += num_written; + } +out: + btrfs_inode_unlock(inode, ilock_flags); return num_written ? num_written : ret; } -static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from) +static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info, + const struct iov_iter *iter, loff_t offset) +{ + const u32 blocksize_mask = fs_info->sectorsize - 1; + + if (offset & blocksize_mask) + return -EINVAL; + + if (iov_iter_alignment(iter) & blocksize_mask) + return -EINVAL; + + return 0; +} + +static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); + struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); loff_t pos; - ssize_t written; + ssize_t written = 0; ssize_t written_buffered; + size_t prev_left = 0; loff_t endbyte; - int err; + ssize_t err; + unsigned int ilock_flags = 0; + struct iomap_dio *dio; + + if (iocb->ki_flags & IOCB_NOWAIT) + ilock_flags |= BTRFS_ILOCK_TRY; - written = generic_file_direct_write(iocb, from); + /* If the write DIO is within EOF, use a shared lock */ + if (iocb->ki_pos + iov_iter_count(from) <= i_size_read(inode)) + ilock_flags |= BTRFS_ILOCK_SHARED; - if (written < 0 || !iov_iter_count(from)) - return written; +relock: + err = btrfs_inode_lock(inode, ilock_flags); + if (err < 0) + return err; + + err = generic_write_checks(iocb, from); + if (err <= 0) { + btrfs_inode_unlock(inode, ilock_flags); + return err; + } + + err = btrfs_write_check(iocb, from, err); + if (err < 0) { + btrfs_inode_unlock(inode, ilock_flags); + goto out; + } + + pos = iocb->ki_pos; + /* + * Re-check since file size may have changed just before taking the + * lock or pos may have changed because of O_APPEND in generic_write_check() + */ + if ((ilock_flags & BTRFS_ILOCK_SHARED) && + pos + iov_iter_count(from) > i_size_read(inode)) { + btrfs_inode_unlock(inode, ilock_flags); + ilock_flags &= ~BTRFS_ILOCK_SHARED; + goto relock; + } + + if (check_direct_IO(fs_info, from, pos)) { + btrfs_inode_unlock(inode, ilock_flags); + goto buffered; + } + + /* + * The iov_iter can be mapped to the same file range we are writing to. + * If that's the case, then we will deadlock in the iomap code, because + * it first calls our callback btrfs_dio_iomap_begin(), which will create + * an ordered extent, and after that it will fault in the pages that the + * iov_iter refers to. During the fault in we end up in the readahead + * pages code (starting at btrfs_readahead()), which will lock the range, + * find that ordered extent and then wait for it to complete (at + * btrfs_lock_and_flush_ordered_range()), resulting in a deadlock since + * obviously the ordered extent can never complete as we didn't submit + * yet the respective bio(s). This always happens when the buffer is + * memory mapped to the same file range, since the iomap DIO code always + * invalidates pages in the target file range (after starting and waiting + * for any writeback). + * + * So here we disable page faults in the iov_iter and then retry if we + * got -EFAULT, faulting in the pages before the retry. + */ + from->nofault = true; + dio = btrfs_dio_write(iocb, from, written); + from->nofault = false; + + /* + * iomap_dio_complete() will call btrfs_sync_file() if we have a dsync + * iocb, and that needs to lock the inode. So unlock it before calling + * iomap_dio_complete() to avoid a deadlock. + */ + btrfs_inode_unlock(inode, ilock_flags); + + if (IS_ERR_OR_NULL(dio)) + err = PTR_ERR_OR_ZERO(dio); + else + err = iomap_dio_complete(dio); + + /* No increment (+=) because iomap returns a cumulative value. */ + if (err > 0) + written = err; + + if (iov_iter_count(from) > 0 && (err == -EFAULT || err > 0)) { + const size_t left = iov_iter_count(from); + /* + * We have more data left to write. Try to fault in as many as + * possible of the remainder pages and retry. We do this without + * releasing and locking again the inode, to prevent races with + * truncate. + * + * Also, in case the iov refers to pages in the file range of the + * file we want to write to (due to a mmap), we could enter an + * infinite loop if we retry after faulting the pages in, since + * iomap will invalidate any pages in the range early on, before + * it tries to fault in the pages of the iov. So we keep track of + * how much was left of iov in the previous EFAULT and fallback + * to buffered IO in case we haven't made any progress. + */ + if (left == prev_left) { + err = -ENOTBLK; + } else { + fault_in_iov_iter_readable(from, left); + prev_left = left; + goto relock; + } + } + + /* + * If 'err' is -ENOTBLK or we have not written all data, then it means + * we must fallback to buffered IO. + */ + if ((err < 0 && err != -ENOTBLK) || !iov_iter_count(from)) + goto out; + +buffered: + /* + * If we are in a NOWAIT context, then return -EAGAIN to signal the caller + * it must retry the operation in a context where blocking is acceptable, + * since we currently don't have NOWAIT semantics support for buffered IO + * and may block there for many reasons (reserving space for example). + */ + if (iocb->ki_flags & IOCB_NOWAIT) { + err = -EAGAIN; + goto out; + } pos = iocb->ki_pos; written_buffered = btrfs_buffered_write(iocb, from); @@ -1858,150 +1917,91 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from) invalidate_mapping_pages(file->f_mapping, pos >> PAGE_SHIFT, endbyte >> PAGE_SHIFT); out: - return written ? written : err; -} - -static void update_time_for_write(struct inode *inode) -{ - struct timespec64 now; - - if (IS_NOCMTIME(inode)) - return; - - now = current_time(inode); - if (!timespec64_equal(&inode->i_mtime, &now)) - inode->i_mtime = now; - - if (!timespec64_equal(&inode->i_ctime, &now)) - inode->i_ctime = now; - - if (IS_I_VERSION(inode)) - inode_inc_iversion(inode); + return err < 0 ? err : written; } -static ssize_t btrfs_file_write_iter(struct kiocb *iocb, - struct iov_iter *from) +static ssize_t btrfs_encoded_write(struct kiocb *iocb, struct iov_iter *from, + const struct btrfs_ioctl_encoded_io_args *encoded) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; - u64 start_pos; - u64 end_pos; - ssize_t num_written = 0; - const bool sync = iocb->ki_flags & IOCB_DSYNC; - ssize_t err; - loff_t pos; - size_t count; - loff_t oldsize; - int clean_page = 0; + loff_t count; + ssize_t ret; - if (!(iocb->ki_flags & IOCB_DIRECT) && - (iocb->ki_flags & IOCB_NOWAIT)) - return -EOPNOTSUPP; - - if (iocb->ki_flags & IOCB_NOWAIT) { - if (!inode_trylock(inode)) - return -EAGAIN; - } else { - inode_lock(inode); - } - - err = generic_write_checks(iocb, from); - if (err <= 0) { - inode_unlock(inode); - return err; - } - - pos = iocb->ki_pos; - count = iov_iter_count(from); - if (iocb->ki_flags & IOCB_NOWAIT) { + btrfs_inode_lock(inode, 0); + count = encoded->len; + ret = generic_write_checks_count(iocb, &count); + if (ret == 0 && count != encoded->len) { /* - * We will allocate space in case nodatacow is not set, - * so bail + * The write got truncated by generic_write_checks_count(). We + * can't do a partial encoded write. */ - if (!(BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | - BTRFS_INODE_PREALLOC)) || - check_can_nocow(BTRFS_I(inode), pos, &count) <= 0) { - inode_unlock(inode); - return -EAGAIN; - } + ret = -EFBIG; } - - current->backing_dev_info = inode_to_bdi(inode); - err = file_remove_privs(file); - if (err) { - inode_unlock(inode); + if (ret || encoded->len == 0) goto out; - } - /* - * If BTRFS flips readonly due to some impossible error - * (fs_info->fs_state now has BTRFS_SUPER_FLAG_ERROR), - * although we have opened a file as writable, we have - * to stop this write operation to ensure FS consistency. - */ - if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) { - inode_unlock(inode); - err = -EROFS; + ret = btrfs_write_check(iocb, from, encoded->len); + if (ret < 0) goto out; - } + + ret = btrfs_do_encoded_write(iocb, from, encoded); +out: + btrfs_inode_unlock(inode, 0); + return ret; +} + +ssize_t btrfs_do_write_iter(struct kiocb *iocb, struct iov_iter *from, + const struct btrfs_ioctl_encoded_io_args *encoded) +{ + struct file *file = iocb->ki_filp; + struct btrfs_inode *inode = BTRFS_I(file_inode(file)); + ssize_t num_written, num_sync; + const bool sync = iocb_is_dsync(iocb); /* - * We reserve space for updating the inode when we reserve space for the - * extent we are going to write, so we will enospc out there. We don't - * need to start yet another transaction to update the inode as we will - * update the inode when we finish writing whatever data we write. + * If the fs flips readonly due to some impossible error, although we + * have opened a file as writable, we have to stop this write operation + * to ensure consistency. */ - update_time_for_write(inode); + if (BTRFS_FS_ERROR(inode->root->fs_info)) + return -EROFS; - start_pos = round_down(pos, fs_info->sectorsize); - oldsize = i_size_read(inode); - if (start_pos > oldsize) { - /* Expand hole size to cover write data, preventing empty gap */ - end_pos = round_up(pos + count, - fs_info->sectorsize); - err = btrfs_cont_expand(inode, oldsize, end_pos); - if (err) { - inode_unlock(inode); - goto out; - } - if (start_pos > round_up(oldsize, fs_info->sectorsize)) - clean_page = 1; - } + if (encoded && (iocb->ki_flags & IOCB_NOWAIT)) + return -EOPNOTSUPP; if (sync) - atomic_inc(&BTRFS_I(inode)->sync_writers); - - if (iocb->ki_flags & IOCB_DIRECT) { - num_written = __btrfs_direct_write(iocb, from); + atomic_inc(&inode->sync_writers); + + if (encoded) { + num_written = btrfs_encoded_write(iocb, from, encoded); + num_sync = encoded->len; + } else if (iocb->ki_flags & IOCB_DIRECT) { + num_written = btrfs_direct_write(iocb, from); + num_sync = num_written; } else { num_written = btrfs_buffered_write(iocb, from); - if (num_written > 0) - iocb->ki_pos = pos + num_written; - if (clean_page) - pagecache_isize_extended(inode, oldsize, - i_size_read(inode)); + num_sync = num_written; } - inode_unlock(inode); + btrfs_set_inode_last_sub_trans(inode); - /* - * We also have to set last_sub_trans to the current log transid, - * otherwise subsequent syncs to a file that's been synced in this - * transaction will appear to have already occurred. - */ - spin_lock(&BTRFS_I(inode)->lock); - BTRFS_I(inode)->last_sub_trans = root->log_transid; - spin_unlock(&BTRFS_I(inode)->lock); - if (num_written > 0) - num_written = generic_write_sync(iocb, num_written); + if (num_sync > 0) { + num_sync = generic_write_sync(iocb, num_sync); + if (num_sync < 0) + num_written = num_sync; + } if (sync) - atomic_dec(&BTRFS_I(inode)->sync_writers); -out: + atomic_dec(&inode->sync_writers); + current->backing_dev_info = NULL; - return num_written ? num_written : err; + return num_written; +} + +static ssize_t btrfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + return btrfs_do_write_iter(iocb, from, NULL); } int btrfs_release_file(struct inode *inode, struct file *filp) @@ -2014,12 +2014,12 @@ int btrfs_release_file(struct inode *inode, struct file *filp) filp->private_data = NULL; /* - * ordered_data_close is set by setattr when we are about to truncate - * a file from a non-zero size to a zero size. This tries to - * flush down new bytes that may have been written if the - * application were using truncate to replace a file in place. + * Set by setattr when we are about to truncate a file from a non-zero + * size to a zero size. This tries to flush down new bytes that may + * have been written if the application were using truncate to replace + * a file in place. */ - if (test_and_clear_bit(BTRFS_INODE_ORDERED_DATA_CLOSE, + if (test_and_clear_bit(BTRFS_INODE_FLUSH_ON_CLOSE, &BTRFS_I(inode)->runtime_flags)) filemap_flush(inode->i_mapping); return 0; @@ -2045,6 +2045,30 @@ static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end) return ret; } +static inline bool skip_inode_logging(const struct btrfs_log_ctx *ctx) +{ + struct btrfs_inode *inode = BTRFS_I(ctx->inode); + struct btrfs_fs_info *fs_info = inode->root->fs_info; + + if (btrfs_inode_in_log(inode, fs_info->generation) && + list_empty(&ctx->ordered_extents)) + return true; + + /* + * If we are doing a fast fsync we can not bail out if the inode's + * last_trans is <= then the last committed transaction, because we only + * update the last_trans of the inode during ordered extent completion, + * and for a fast fsync we don't wait for that, we only wait for the + * writeback to complete. + */ + if (inode->last_trans <= fs_info->last_trans_committed && + (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags) || + list_empty(&ctx->ordered_extents))) + return true; + + return false; +} + /* * fsync call for both files and directories. This logs the inode into * the tree log instead of forcing full commits whenever possible. @@ -2065,12 +2089,26 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) struct btrfs_trans_handle *trans; struct btrfs_log_ctx ctx; int ret = 0, err; + u64 len; + bool full_sync; trace_btrfs_sync_file(file, datasync); btrfs_init_log_ctx(&ctx, inode); /* + * Always set the range to a full range, otherwise we can get into + * several problems, from missing file extent items to represent holes + * when not using the NO_HOLES feature, to log tree corruption due to + * races between hole detection during logging and completion of ordered + * extents outside the range, to missing checksums due to ordered extents + * for which we flushed only a subset of their pages. + */ + start = 0; + end = LLONG_MAX; + len = (u64)LLONG_MAX + 1; + + /* * We write the dirty pages in the range and wait until they complete * out of the ->i_mutex. If so, we can flush the dirty pages by * multi-task, and make the performance up. See @@ -2080,36 +2118,16 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) if (ret) goto out; - inode_lock(inode); - - /* - * We take the dio_sem here because the tree log stuff can race with - * lockless dio writes and get an extent map logged for an extent we - * never waited on. We need it this high up for lockdep reasons. - */ - down_write(&BTRFS_I(inode)->dio_sem); + btrfs_inode_lock(inode, BTRFS_ILOCK_MMAP); atomic_inc(&root->log_batch); /* - * If the inode needs a full sync, make sure we use a full range to - * avoid log tree corruption, due to hole detection racing with ordered - * extent completion for adjacent ranges, and assertion failures during - * hole detection. Do this while holding the inode lock, to avoid races - * with other tasks. - */ - if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, - &BTRFS_I(inode)->runtime_flags)) { - start = 0; - end = LLONG_MAX; - } - - /* - * Before we acquired the inode's lock, someone may have dirtied more - * pages in the target range. We need to make sure that writeback for - * any such pages does not start while we are logging the inode, because - * if it does, any of the following might happen when we are not doing a - * full inode sync: + * Before we acquired the inode's lock and the mmap lock, someone may + * have dirtied more pages in the target range. We need to make sure + * that writeback for any such pages does not start while we are logging + * the inode, because if it does, any of the following might happen when + * we are not doing a full inode sync: * * 1) We log an extent after its writeback finishes but before its * checksums are added to the csum tree, leading to -EIO errors @@ -2124,28 +2142,56 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) */ ret = start_ordered_ops(inode, start, end); if (ret) { - inode_unlock(inode); + btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP); goto out; } /* + * Always check for the full sync flag while holding the inode's lock, + * to avoid races with other tasks. The flag must be either set all the + * time during logging or always off all the time while logging. + * We check the flag here after starting delalloc above, because when + * running delalloc the full sync flag may be set if we need to drop + * extra extent map ranges due to temporary memory allocation failures. + */ + full_sync = test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, + &BTRFS_I(inode)->runtime_flags); + + /* * We have to do this here to avoid the priority inversion of waiting on * IO of a lower priority task while holding a transaction open. * - * Also, the range length can be represented by u64, we have to do the - * typecasts to avoid signed overflow if it's [0, LLONG_MAX]. + * For a full fsync we wait for the ordered extents to complete while + * for a fast fsync we wait just for writeback to complete, and then + * attach the ordered extents to the transaction so that a transaction + * commit waits for their completion, to avoid data loss if we fsync, + * the current transaction commits before the ordered extents complete + * and a power failure happens right after that. + * + * For zoned filesystem, if a write IO uses a ZONE_APPEND command, the + * logical address recorded in the ordered extent may change. We need + * to wait for the IO to stabilize the logical address. */ - ret = btrfs_wait_ordered_range(inode, start, (u64)end - (u64)start + 1); - if (ret) { - up_write(&BTRFS_I(inode)->dio_sem); - inode_unlock(inode); - goto out; + if (full_sync || btrfs_is_zoned(fs_info)) { + ret = btrfs_wait_ordered_range(inode, start, len); + } else { + /* + * Get our ordered extents as soon as possible to avoid doing + * checksum lookups in the csum tree, and use instead the + * checksums attached to the ordered extents. + */ + btrfs_get_ordered_extents_for_logging(BTRFS_I(inode), + &ctx.ordered_extents); + ret = filemap_fdatawait_range(inode->i_mapping, start, end); } + + if (ret) + goto out_release_extents; + atomic_inc(&root->log_batch); smp_mb(); - if (btrfs_inode_in_log(BTRFS_I(inode), fs_info->generation) || - BTRFS_I(inode)->last_trans <= fs_info->last_trans_committed) { + if (skip_inode_logging(&ctx)) { /* * We've had everything committed since the last time we were * modified so clear this flag in case it was set for whatever @@ -2161,9 +2207,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) * checked called fsync. */ ret = filemap_check_wb_err(inode->i_mapping, file->f_wb_err); - up_write(&BTRFS_I(inode)->dio_sem); - inode_unlock(inode); - goto out; + goto out_release_extents; } /* @@ -2180,15 +2224,15 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); - up_write(&BTRFS_I(inode)->dio_sem); - inode_unlock(inode); - goto out; + goto out_release_extents; } + trans->in_fsync = true; - ret = btrfs_log_dentry_safe(trans, dentry, start, end, &ctx); + ret = btrfs_log_dentry_safe(trans, dentry, &ctx); + btrfs_release_log_ctx_extents(&ctx); if (ret < 0) { /* Fallthrough and commit/free transaction. */ - ret = 1; + ret = BTRFS_LOG_FORCE_COMMIT; } /* we've logged all the items and now have a consistent @@ -2201,27 +2245,76 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) * file again, but that will end up using the synchronization * inside btrfs_sync_log to keep things safe. */ - up_write(&BTRFS_I(inode)->dio_sem); - inode_unlock(inode); + btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP); - if (ret != BTRFS_NO_LOG_SYNC) { + if (ret == BTRFS_NO_LOG_SYNC) { + ret = btrfs_end_transaction(trans); + goto out; + } + + /* We successfully logged the inode, attempt to sync the log. */ + if (!ret) { + ret = btrfs_sync_log(trans, root, &ctx); if (!ret) { - ret = btrfs_sync_log(trans, root, &ctx); - if (!ret) { - ret = btrfs_end_transaction(trans); - goto out; - } + ret = btrfs_end_transaction(trans); + goto out; } - ret = btrfs_commit_transaction(trans); - } else { + } + + /* + * At this point we need to commit the transaction because we had + * btrfs_need_log_full_commit() or some other error. + * + * If we didn't do a full sync we have to stop the trans handle, wait on + * the ordered extents, start it again and commit the transaction. If + * we attempt to wait on the ordered extents here we could deadlock with + * something like fallocate() that is holding the extent lock trying to + * start a transaction while some other thread is trying to commit the + * transaction while we (fsync) are currently holding the transaction + * open. + */ + if (!full_sync) { ret = btrfs_end_transaction(trans); + if (ret) + goto out; + ret = btrfs_wait_ordered_range(inode, start, len); + if (ret) + goto out; + + /* + * This is safe to use here because we're only interested in + * making sure the transaction that had the ordered extents is + * committed. We aren't waiting on anything past this point, + * we're purely getting the transaction and committing it. + */ + trans = btrfs_attach_transaction_barrier(root); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + + /* + * We committed the transaction and there's no currently + * running transaction, this means everything we care + * about made it to disk and we are done. + */ + if (ret == -ENOENT) + ret = 0; + goto out; + } } + + ret = btrfs_commit_transaction(trans); out: ASSERT(list_empty(&ctx.list)); + ASSERT(list_empty(&ctx.conflict_inodes)); err = file_check_and_advance_wb_err(file); if (!ret) ret = err; return ret > 0 ? -EIO : ret; + +out_release_extents: + btrfs_release_log_ctx_extents(&ctx); + btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP); + goto out; } static const struct vm_operations_struct btrfs_file_vm_ops = { @@ -2234,7 +2327,7 @@ static int btrfs_file_mmap(struct file *filp, struct vm_area_struct *vma) { struct address_space *mapping = filp->f_mapping; - if (!mapping->a_ops->readpage) + if (!mapping->a_ops->read_folio) return -ENOEXEC; file_accessed(filp); @@ -2281,7 +2374,6 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct extent_buffer *leaf; struct btrfs_file_extent_item *fi; struct extent_map *hole_em; - struct extent_map_tree *em_tree = &inode->extent_tree; struct btrfs_key key; int ret; @@ -2315,6 +2407,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, btrfs_set_file_extent_num_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_offset(leaf, fi, 0); + btrfs_set_file_extent_generation(leaf, fi, trans->transid); btrfs_mark_buffer_dirty(leaf); goto out; } @@ -2331,13 +2424,14 @@ static int fill_holes(struct btrfs_trans_handle *trans, btrfs_set_file_extent_num_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_offset(leaf, fi, 0); + btrfs_set_file_extent_generation(leaf, fi, trans->transid); btrfs_mark_buffer_dirty(leaf); goto out; } btrfs_release_path(path); - ret = btrfs_insert_file_extent(trans, root, btrfs_ino(inode), - offset, 0, 0, end - offset, 0, end - offset, 0, 0, 0); + ret = btrfs_insert_hole_extent(trans, root, btrfs_ino(inode), offset, + end - offset); if (ret) return ret; @@ -2346,8 +2440,8 @@ out: hole_em = alloc_extent_map(); if (!hole_em) { - btrfs_drop_extent_cache(inode, offset, end - 1, 0); - set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags); + btrfs_drop_extent_map_range(inode, offset, end - 1, false); + btrfs_set_inode_full_sync(inode); } else { hole_em->start = offset; hole_em->len = end - offset; @@ -2360,16 +2454,10 @@ out: hole_em->compress_type = BTRFS_COMPRESS_NONE; hole_em->generation = trans->transid; - do { - btrfs_drop_extent_cache(inode, offset, end - 1, 0); - write_lock(&em_tree->lock); - ret = add_extent_mapping(em_tree, hole_em, 1); - write_unlock(&em_tree->lock); - } while (ret == -EEXIST); + ret = btrfs_replace_extent_map_range(inode, hole_em, true); free_extent_map(hole_em); if (ret) - set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, - &inode->runtime_flags); + btrfs_set_inode_full_sync(inode); } return 0; @@ -2381,13 +2469,13 @@ out: * em->start + em->len > start) * When a hole extent is found, return 1 and modify start/len. */ -static int find_first_non_hole(struct inode *inode, u64 *start, u64 *len) +static int find_first_non_hole(struct btrfs_inode *inode, u64 *start, u64 *len) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode->root->fs_info; struct extent_map *em; int ret = 0; - em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, + em = btrfs_get_extent(inode, NULL, 0, round_down(*start, fs_info->sectorsize), round_up(*len, fs_info->sectorsize)); if (IS_ERR(em)) @@ -2404,100 +2492,129 @@ static int find_first_non_hole(struct inode *inode, u64 *start, u64 *len) return ret; } -static int btrfs_punch_hole_lock_range(struct inode *inode, - const u64 lockstart, - const u64 lockend, - struct extent_state **cached_state) +static void btrfs_punch_hole_lock_range(struct inode *inode, + const u64 lockstart, + const u64 lockend, + struct extent_state **cached_state) { - while (1) { - struct btrfs_ordered_extent *ordered; - int ret; + /* + * For subpage case, if the range is not at page boundary, we could + * have pages at the leading/tailing part of the range. + * This could lead to dead loop since filemap_range_has_page() + * will always return true. + * So here we need to do extra page alignment for + * filemap_range_has_page(). + */ + const u64 page_lockstart = round_up(lockstart, PAGE_SIZE); + const u64 page_lockend = round_down(lockend + 1, PAGE_SIZE) - 1; + while (1) { truncate_pagecache_range(inode, lockstart, lockend); - lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend, - cached_state); - ordered = btrfs_lookup_first_ordered_extent(inode, lockend); - + lock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend, + cached_state); /* - * We need to make sure we have no ordered extents in this range - * and nobody raced in and read a page in this range, if we did - * we need to try again. + * We can't have ordered extents in the range, nor dirty/writeback + * pages, because we have locked the inode's VFS lock in exclusive + * mode, we have locked the inode's i_mmap_lock in exclusive mode, + * we have flushed all delalloc in the range and we have waited + * for any ordered extents in the range to complete. + * We can race with anyone reading pages from this range, so after + * locking the range check if we have pages in the range, and if + * we do, unlock the range and retry. */ - if ((!ordered || - (ordered->file_offset + ordered->num_bytes <= lockstart || - ordered->file_offset > lockend)) && - !filemap_range_has_page(inode->i_mapping, - lockstart, lockend)) { - if (ordered) - btrfs_put_ordered_extent(ordered); + if (!filemap_range_has_page(inode->i_mapping, page_lockstart, + page_lockend)) break; - } - if (ordered) - btrfs_put_ordered_extent(ordered); - unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, - lockend, cached_state); - ret = btrfs_wait_ordered_range(inode, lockstart, - lockend - lockstart + 1); - if (ret) - return ret; + + unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend, + cached_state); } - return 0; + + btrfs_assert_inode_range_clean(BTRFS_I(inode), lockstart, lockend); } -static int btrfs_insert_clone_extent(struct btrfs_trans_handle *trans, - struct inode *inode, +static int btrfs_insert_replace_extent(struct btrfs_trans_handle *trans, + struct btrfs_inode *inode, struct btrfs_path *path, - struct btrfs_clone_extent_info *clone_info, - const u64 clone_len) + struct btrfs_replace_extent_info *extent_info, + const u64 replace_len, + const u64 bytes_to_drop) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_root *root = inode->root; struct btrfs_file_extent_item *extent; struct extent_buffer *leaf; struct btrfs_key key; int slot; struct btrfs_ref ref = { 0 }; - u64 ref_offset; int ret; - if (clone_len == 0) + if (replace_len == 0) return 0; - if (clone_info->disk_offset == 0 && - btrfs_fs_incompat(fs_info, NO_HOLES)) + if (extent_info->disk_offset == 0 && + btrfs_fs_incompat(fs_info, NO_HOLES)) { + btrfs_update_inode_bytes(inode, 0, bytes_to_drop); return 0; + } - key.objectid = btrfs_ino(BTRFS_I(inode)); + key.objectid = btrfs_ino(inode); key.type = BTRFS_EXTENT_DATA_KEY; - key.offset = clone_info->file_offset; + key.offset = extent_info->file_offset; ret = btrfs_insert_empty_item(trans, root, path, &key, - clone_info->item_size); + sizeof(struct btrfs_file_extent_item)); if (ret) return ret; leaf = path->nodes[0]; slot = path->slots[0]; - write_extent_buffer(leaf, clone_info->extent_buf, + write_extent_buffer(leaf, extent_info->extent_buf, btrfs_item_ptr_offset(leaf, slot), - clone_info->item_size); + sizeof(struct btrfs_file_extent_item)); extent = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); - btrfs_set_file_extent_offset(leaf, extent, clone_info->data_offset); - btrfs_set_file_extent_num_bytes(leaf, extent, clone_len); + ASSERT(btrfs_file_extent_type(leaf, extent) != BTRFS_FILE_EXTENT_INLINE); + btrfs_set_file_extent_offset(leaf, extent, extent_info->data_offset); + btrfs_set_file_extent_num_bytes(leaf, extent, replace_len); + if (extent_info->is_new_extent) + btrfs_set_file_extent_generation(leaf, extent, trans->transid); btrfs_mark_buffer_dirty(leaf); btrfs_release_path(path); + ret = btrfs_inode_set_file_extent_range(inode, extent_info->file_offset, + replace_len); + if (ret) + return ret; + /* If it's a hole, nothing more needs to be done. */ - if (clone_info->disk_offset == 0) + if (extent_info->disk_offset == 0) { + btrfs_update_inode_bytes(inode, 0, bytes_to_drop); return 0; + } - inode_add_bytes(inode, clone_len); - btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, - clone_info->disk_offset, - clone_info->disk_len, 0); - ref_offset = clone_info->file_offset - clone_info->data_offset; - btrfs_init_data_ref(&ref, root->root_key.objectid, - btrfs_ino(BTRFS_I(inode)), ref_offset); - ret = btrfs_inc_extent_ref(trans, &ref); + btrfs_update_inode_bytes(inode, replace_len, bytes_to_drop); + + if (extent_info->is_new_extent && extent_info->insertions == 0) { + key.objectid = extent_info->disk_offset; + key.type = BTRFS_EXTENT_ITEM_KEY; + key.offset = extent_info->disk_len; + ret = btrfs_alloc_reserved_file_extent(trans, root, + btrfs_ino(inode), + extent_info->file_offset, + extent_info->qgroup_reserved, + &key); + } else { + u64 ref_offset; + + btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, + extent_info->disk_offset, + extent_info->disk_len, 0); + ref_offset = extent_info->file_offset - extent_info->data_offset; + btrfs_init_data_ref(&ref, root->root_key.objectid, + btrfs_ino(inode), ref_offset, 0, false); + ret = btrfs_inc_extent_ref(trans, &ref); + } + + extent_info->insertions++; return ret; } @@ -2505,26 +2622,27 @@ static int btrfs_insert_clone_extent(struct btrfs_trans_handle *trans, /* * The respective range must have been previously locked, as well as the inode. * The end offset is inclusive (last byte of the range). - * @clone_info is NULL for fallocate's hole punching and non-NULL for extent - * cloning. - * When cloning, we don't want to end up in a state where we dropped extents - * without inserting a new one, so we must abort the transaction to avoid a - * corruption. + * @extent_info is NULL for fallocate's hole punching and non-NULL when replacing + * the file range with an extent. + * When not punching a hole, we don't want to end up in a state where we dropped + * extents without inserting a new one, so we must abort the transaction to avoid + * a corruption. */ -int btrfs_punch_hole_range(struct inode *inode, struct btrfs_path *path, - const u64 start, const u64 end, - struct btrfs_clone_extent_info *clone_info, - struct btrfs_trans_handle **trans_out) +int btrfs_replace_file_extents(struct btrfs_inode *inode, + struct btrfs_path *path, const u64 start, + const u64 end, + struct btrfs_replace_extent_info *extent_info, + struct btrfs_trans_handle **trans_out) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_drop_extents_args drop_args = { 0 }; + struct btrfs_root *root = inode->root; + struct btrfs_fs_info *fs_info = root->fs_info; u64 min_size = btrfs_calc_insert_metadata_size(fs_info, 1); - u64 ino_size = round_up(inode->i_size, fs_info->sectorsize); - struct btrfs_root *root = BTRFS_I(inode)->root; + u64 ino_size = round_up(inode->vfs_inode.i_size, fs_info->sectorsize); struct btrfs_trans_handle *trans = NULL; struct btrfs_block_rsv *rsv; unsigned int rsv_count; u64 cur_offset; - u64 drop_end; u64 len = end - start; int ret = 0; @@ -2537,15 +2655,15 @@ int btrfs_punch_hole_range(struct inode *inode, struct btrfs_path *path, goto out; } rsv->size = btrfs_calc_insert_metadata_size(fs_info, 1); - rsv->failfast = 1; + rsv->failfast = true; /* * 1 - update the inode * 1 - removing the extents in the range - * 1 - adding the hole extent if no_holes isn't set or if we are cloning - * an extent + * 1 - adding the hole extent if no_holes isn't set or if we are + * replacing the range with a new extent */ - if (!btrfs_fs_incompat(fs_info, NO_HOLES) || clone_info) + if (!btrfs_fs_incompat(fs_info, NO_HOLES) || extent_info) rsv_count = 3; else rsv_count = 2; @@ -2559,33 +2677,43 @@ int btrfs_punch_hole_range(struct inode *inode, struct btrfs_path *path, ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv, rsv, min_size, false); - BUG_ON(ret); + if (WARN_ON(ret)) + goto out_trans; trans->block_rsv = rsv; cur_offset = start; + drop_args.path = path; + drop_args.end = end + 1; + drop_args.drop_cache = true; while (cur_offset < end) { - ret = __btrfs_drop_extents(trans, root, inode, path, - cur_offset, end + 1, &drop_end, - 1, 0, 0, NULL); + drop_args.start = cur_offset; + ret = btrfs_drop_extents(trans, root, inode, &drop_args); + /* If we are punching a hole decrement the inode's byte count */ + if (!extent_info) + btrfs_update_inode_bytes(inode, 0, + drop_args.bytes_found); if (ret != -ENOSPC) { /* - * When cloning we want to avoid transaction aborts when - * nothing was done and we are attempting to clone parts - * of inline extents, in such cases -EOPNOTSUPP is - * returned by __btrfs_drop_extents() without having - * changed anything in the file. + * The only time we don't want to abort is if we are + * attempting to clone a partial inline extent, in which + * case we'll get EOPNOTSUPP. However if we aren't + * clone we need to abort no matter what, because if we + * got EOPNOTSUPP via prealloc then we messed up and + * need to abort. */ - if (clone_info && ret && ret != -EOPNOTSUPP) + if (ret && + (ret != -EOPNOTSUPP || + (extent_info && extent_info->is_new_extent))) btrfs_abort_transaction(trans, ret); break; } trans->block_rsv = &fs_info->trans_block_rsv; - if (!clone_info && cur_offset < drop_end && + if (!extent_info && cur_offset < drop_args.drop_end && cur_offset < ino_size) { - ret = fill_holes(trans, BTRFS_I(inode), path, - cur_offset, drop_end); + ret = fill_holes(trans, inode, path, cur_offset, + drop_args.drop_end); if (ret) { /* * If we failed then we didn't insert our hole @@ -2596,23 +2724,62 @@ int btrfs_punch_hole_range(struct inode *inode, struct btrfs_path *path, btrfs_abort_transaction(trans, ret); break; } + } else if (!extent_info && cur_offset < drop_args.drop_end) { + /* + * We are past the i_size here, but since we didn't + * insert holes we need to clear the mapped area so we + * know to not set disk_i_size in this area until a new + * file extent is inserted here. + */ + ret = btrfs_inode_clear_file_extent_range(inode, + cur_offset, + drop_args.drop_end - cur_offset); + if (ret) { + /* + * We couldn't clear our area, so we could + * presumably adjust up and corrupt the fs, so + * we need to abort. + */ + btrfs_abort_transaction(trans, ret); + break; + } } - if (clone_info && drop_end > clone_info->file_offset) { - u64 clone_len = drop_end - clone_info->file_offset; + if (extent_info && + drop_args.drop_end > extent_info->file_offset) { + u64 replace_len = drop_args.drop_end - + extent_info->file_offset; - ret = btrfs_insert_clone_extent(trans, inode, path, - clone_info, clone_len); + ret = btrfs_insert_replace_extent(trans, inode, path, + extent_info, replace_len, + drop_args.bytes_found); if (ret) { btrfs_abort_transaction(trans, ret); break; } - clone_info->data_len -= clone_len; - clone_info->data_offset += clone_len; - clone_info->file_offset += clone_len; + extent_info->data_len -= replace_len; + extent_info->data_offset += replace_len; + extent_info->file_offset += replace_len; } - cur_offset = drop_end; + /* + * We are releasing our handle on the transaction, balance the + * dirty pages of the btree inode and flush delayed items, and + * then get a new transaction handle, which may now point to a + * new transaction in case someone else may have committed the + * transaction we used to replace/drop file extent items. So + * bump the inode's iversion and update mtime and ctime except + * if we are called from a dedupe context. This is because a + * power failure/crash may happen after the transaction is + * committed and before we finish replacing/dropping all the + * file extent items we need. + */ + inode_inc_iversion(&inode->vfs_inode); + + if (!extent_info || extent_info->update_times) { + inode->vfs_inode.i_mtime = current_time(&inode->vfs_inode); + inode->vfs_inode.i_ctime = inode->vfs_inode.i_mtime; + } ret = btrfs_update_inode(trans, root, inode); if (ret) @@ -2630,10 +2797,13 @@ int btrfs_punch_hole_range(struct inode *inode, struct btrfs_path *path, ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv, rsv, min_size, false); - BUG_ON(ret); /* shouldn't happen */ + if (WARN_ON(ret)) + break; trans->block_rsv = rsv; - if (!clone_info) { + cur_offset = drop_args.drop_end; + len = end - cur_offset; + if (!extent_info && len) { ret = find_first_non_hole(inode, &cur_offset, &len); if (unlikely(ret < 0)) break; @@ -2647,14 +2817,11 @@ int btrfs_punch_hole_range(struct inode *inode, struct btrfs_path *path, /* * If we were cloning, force the next fsync to be a full one since we * we replaced (or just dropped in the case of cloning holes when - * NO_HOLES is enabled) extents and extent maps. - * This is for the sake of simplicity, and cloning into files larger - * than 16Mb would force the full fsync any way (when - * try_release_extent_mapping() is invoked during page cache truncation. + * NO_HOLES is enabled) file extent items and did not setup new extent + * maps for the replacement extents (or holes). */ - if (clone_info) - set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, - &BTRFS_I(inode)->runtime_flags); + if (extent_info && !extent_info->is_new_extent) + btrfs_set_inode_full_sync(inode); if (ret) goto out_trans; @@ -2671,25 +2838,36 @@ int btrfs_punch_hole_range(struct inode *inode, struct btrfs_path *path, * will not record the existence of the hole region * [existing_hole_start, lockend]. */ - if (drop_end <= end) - drop_end = end + 1; + if (drop_args.drop_end <= end) + drop_args.drop_end = end + 1; /* * Don't insert file hole extent item if it's for a range beyond eof * (because it's useless) or if it represents a 0 bytes range (when * cur_offset == drop_end). */ - if (!clone_info && cur_offset < ino_size && cur_offset < drop_end) { - ret = fill_holes(trans, BTRFS_I(inode), path, - cur_offset, drop_end); + if (!extent_info && cur_offset < ino_size && + cur_offset < drop_args.drop_end) { + ret = fill_holes(trans, inode, path, cur_offset, + drop_args.drop_end); if (ret) { /* Same comment as above. */ btrfs_abort_transaction(trans, ret); goto out_trans; } + } else if (!extent_info && cur_offset < drop_args.drop_end) { + /* See the comment in the loop above for the reasoning here. */ + ret = btrfs_inode_clear_file_extent_range(inode, cur_offset, + drop_args.drop_end - cur_offset); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_trans; + } + } - if (clone_info) { - ret = btrfs_insert_clone_extent(trans, inode, path, clone_info, - clone_info->data_len); + if (extent_info) { + ret = btrfs_insert_replace_extent(trans, inode, path, + extent_info, extent_info->data_len, + drop_args.bytes_found); if (ret) { btrfs_abort_transaction(trans, ret); goto out_trans; @@ -2711,8 +2889,9 @@ out: return ret; } -static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) +static int btrfs_punch_hole(struct file *file, loff_t offset, loff_t len) { + struct inode *inode = file_inode(file); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; struct extent_state *cached_state = NULL; @@ -2729,13 +2908,14 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) bool truncated_block = false; bool updated_inode = false; + btrfs_inode_lock(inode, BTRFS_ILOCK_MMAP); + ret = btrfs_wait_ordered_range(inode, offset, len); if (ret) - return ret; + goto out_only_mutex; - inode_lock(inode); ino_size = round_up(inode->i_size, fs_info->sectorsize); - ret = find_first_non_hole(inode, &offset, &len); + ret = find_first_non_hole(BTRFS_I(inode), &offset, &len); if (ret < 0) goto out_only_mutex; if (ret && !len) { @@ -2744,9 +2924,12 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) goto out_only_mutex; } - lockstart = round_up(offset, btrfs_inode_sectorsize(inode)); - lockend = round_down(offset + len, - btrfs_inode_sectorsize(inode)) - 1; + ret = file_modified(file); + if (ret) + goto out_only_mutex; + + lockstart = round_up(offset, fs_info->sectorsize); + lockend = round_down(offset + len, fs_info->sectorsize) - 1; same_block = (BTRFS_BYTES_TO_BLKS(fs_info, offset)) == (BTRFS_BYTES_TO_BLKS(fs_info, offset + len - 1)); /* @@ -2760,7 +2943,8 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) if (same_block && len < fs_info->sectorsize) { if (offset < ino_size) { truncated_block = true; - ret = btrfs_truncate_block(inode, offset, len, 0); + ret = btrfs_truncate_block(BTRFS_I(inode), offset, len, + 0); } else { ret = 0; } @@ -2770,9 +2954,9 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) /* zero back part of the first block */ if (offset < ino_size) { truncated_block = true; - ret = btrfs_truncate_block(inode, offset, 0, 0); + ret = btrfs_truncate_block(BTRFS_I(inode), offset, 0, 0); if (ret) { - inode_unlock(inode); + btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP); return ret; } } @@ -2785,7 +2969,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) /* after truncate page, check hole again */ len = offset + len - lockstart; offset = lockstart; - ret = find_first_non_hole(inode, &offset, &len); + ret = find_first_non_hole(BTRFS_I(inode), &offset, &len); if (ret < 0) goto out_only_mutex; if (ret && !len) { @@ -2799,14 +2983,14 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) tail_start = lockend + 1; tail_len = offset + len - tail_start; if (tail_len) { - ret = find_first_non_hole(inode, &tail_start, &tail_len); + ret = find_first_non_hole(BTRFS_I(inode), &tail_start, &tail_len); if (unlikely(ret < 0)) goto out_only_mutex; if (!ret) { /* zero the front end of the last page */ if (tail_start + tail_len < ino_size) { truncated_block = true; - ret = btrfs_truncate_block(inode, + ret = btrfs_truncate_block(BTRFS_I(inode), tail_start + tail_len, 0, 1); if (ret) @@ -2820,10 +3004,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) goto out_only_mutex; } - ret = btrfs_punch_hole_lock_range(inode, lockstart, lockend, - &cached_state); - if (ret) - goto out_only_mutex; + btrfs_punch_hole_lock_range(inode, lockstart, lockend, &cached_state); path = btrfs_alloc_path(); if (!path) { @@ -2831,22 +3012,23 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) goto out; } - ret = btrfs_punch_hole_range(inode, path, lockstart, lockend, NULL, - &trans); + ret = btrfs_replace_file_extents(BTRFS_I(inode), path, lockstart, + lockend, NULL, &trans); btrfs_free_path(path); if (ret) goto out; ASSERT(trans != NULL); inode_inc_iversion(inode); - inode->i_mtime = inode->i_ctime = current_time(inode); - ret = btrfs_update_inode(trans, root, inode); + inode->i_mtime = current_time(inode); + inode->i_ctime = inode->i_mtime; + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); updated_inode = true; btrfs_end_transaction(trans); btrfs_btree_balance_dirty(fs_info); out: - unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend, - &cached_state); + unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend, + &cached_state); out_only_mutex: if (!updated_inode && truncated_block && !ret) { /* @@ -2867,13 +3049,13 @@ out_only_mutex: } else { int ret2; - ret = btrfs_update_inode(trans, root, inode); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); ret2 = btrfs_end_transaction(trans); if (!ret) ret = ret2; } } - inode_unlock(inode); + btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP); return ret; } @@ -2892,22 +3074,20 @@ struct falloc_range { */ static int add_falloc_range(struct list_head *head, u64 start, u64 len) { - struct falloc_range *prev = NULL; struct falloc_range *range = NULL; - if (list_empty(head)) - goto insert; - - /* - * As fallocate iterate by bytenr order, we only need to check - * the last range. - */ - prev = list_entry(head->prev, struct falloc_range, list); - if (prev->start + prev->len == start) { - prev->len += len; - return 0; + if (!list_empty(head)) { + /* + * As fallocate iterates by bytenr order, we only need to check + * the last range. + */ + range = list_last_entry(head, struct falloc_range, list); + if (range->start + range->len == start) { + range->len += len; + return 0; + } } -insert: + range = kmalloc(sizeof(*range), GFP_KERNEL); if (!range) return -ENOMEM; @@ -2935,8 +3115,8 @@ static int btrfs_fallocate_update_isize(struct inode *inode, inode->i_ctime = current_time(inode); i_size_write(inode, end); - btrfs_ordered_update_i_size(inode, end, NULL); - ret = btrfs_update_inode(trans, root, inode); + btrfs_inode_safe_disk_i_size_write(BTRFS_I(inode), 0); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); ret2 = btrfs_end_transaction(trans); return ret ? ret : ret2; @@ -2948,15 +3128,15 @@ enum { RANGE_BOUNDARY_HOLE, }; -static int btrfs_zero_range_check_range_boundary(struct inode *inode, +static int btrfs_zero_range_check_range_boundary(struct btrfs_inode *inode, u64 offset) { - const u64 sectorsize = btrfs_inode_sectorsize(inode); + const u64 sectorsize = inode->root->fs_info->sectorsize; struct extent_map *em; int ret; offset = round_down(offset, sectorsize); - em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize); + em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize); if (IS_ERR(em)) return PTR_ERR(em); @@ -2981,14 +3161,12 @@ static int btrfs_zero_range(struct inode *inode, struct extent_changeset *data_reserved = NULL; int ret; u64 alloc_hint = 0; - const u64 sectorsize = btrfs_inode_sectorsize(inode); + const u64 sectorsize = fs_info->sectorsize; u64 alloc_start = round_down(offset, sectorsize); u64 alloc_end = round_up(offset + len, sectorsize); u64 bytes_to_reserve = 0; bool space_reserved = false; - inode_dio_wait(inode); - em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, alloc_start, alloc_end - alloc_start); if (IS_ERR(em)) { @@ -3048,7 +3226,8 @@ static int btrfs_zero_range(struct inode *inode, } if (len < sectorsize && em->block_start != EXTENT_MAP_HOLE) { free_extent_map(em); - ret = btrfs_truncate_block(inode, offset, len, 0); + ret = btrfs_truncate_block(BTRFS_I(inode), offset, len, + 0); if (!ret) ret = btrfs_fallocate_update_isize(inode, offset + len, @@ -3071,14 +3250,15 @@ static int btrfs_zero_range(struct inode *inode, * to cover them. */ if (!IS_ALIGNED(offset, sectorsize)) { - ret = btrfs_zero_range_check_range_boundary(inode, offset); + ret = btrfs_zero_range_check_range_boundary(BTRFS_I(inode), + offset); if (ret < 0) goto out; if (ret == RANGE_BOUNDARY_HOLE) { alloc_start = round_down(offset, sectorsize); ret = 0; } else if (ret == RANGE_BOUNDARY_WRITTEN_EXTENT) { - ret = btrfs_truncate_block(inode, offset, 0, 0); + ret = btrfs_truncate_block(BTRFS_I(inode), offset, 0, 0); if (ret) goto out; } else { @@ -3087,7 +3267,7 @@ static int btrfs_zero_range(struct inode *inode, } if (!IS_ALIGNED(offset + len, sectorsize)) { - ret = btrfs_zero_range_check_range_boundary(inode, + ret = btrfs_zero_range_check_range_boundary(BTRFS_I(inode), offset + len); if (ret < 0) goto out; @@ -3095,7 +3275,8 @@ static int btrfs_zero_range(struct inode *inode, alloc_end = round_up(offset + len, sectorsize); ret = 0; } else if (ret == RANGE_BOUNDARY_WRITTEN_EXTENT) { - ret = btrfs_truncate_block(inode, offset + len, 0, 1); + ret = btrfs_truncate_block(BTRFS_I(inode), offset + len, + 0, 1); if (ret) goto out; } else { @@ -3115,20 +3296,21 @@ reserve_space: if (ret < 0) goto out; space_reserved = true; - ret = btrfs_qgroup_reserve_data(inode, &data_reserved, + btrfs_punch_hole_lock_range(inode, lockstart, lockend, + &cached_state); + ret = btrfs_qgroup_reserve_data(BTRFS_I(inode), &data_reserved, alloc_start, bytes_to_reserve); - if (ret) - goto out; - ret = btrfs_punch_hole_lock_range(inode, lockstart, lockend, - &cached_state); - if (ret) + if (ret) { + unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, + lockend, &cached_state); goto out; + } ret = btrfs_prealloc_file_range(inode, mode, alloc_start, alloc_end - alloc_start, i_blocksize(inode), offset + len, &alloc_hint); - unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, - lockend, &cached_state); + unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend, + &cached_state); /* btrfs_prealloc_file_range releases reserved space on error */ if (ret) { space_reserved = false; @@ -3138,7 +3320,7 @@ reserve_space: ret = btrfs_fallocate_update_isize(inode, offset + len, mode); out: if (ret && space_reserved) - btrfs_free_reserved_data_space(inode, data_reserved, + btrfs_free_reserved_data_space(BTRFS_I(inode), data_reserved, alloc_start, bytes_to_reserve); extent_changeset_free(data_reserved); @@ -3161,10 +3343,17 @@ static long btrfs_fallocate(struct file *file, int mode, u64 alloc_hint = 0; u64 locked_end; u64 actual_end = 0; + u64 data_space_needed = 0; + u64 data_space_reserved = 0; + u64 qgroup_reserved = 0; struct extent_map *em; - int blocksize = btrfs_inode_sectorsize(inode); + int blocksize = BTRFS_I(inode)->root->fs_info->sectorsize; int ret; + /* Do not allow fallocate in ZONED mode */ + if (btrfs_is_zoned(btrfs_sb(inode->i_sb))) + return -EOPNOTSUPP; + alloc_start = round_down(offset, blocksize); alloc_end = round_up(offset + len, blocksize); cur_offset = alloc_start; @@ -3175,21 +3364,9 @@ static long btrfs_fallocate(struct file *file, int mode, return -EOPNOTSUPP; if (mode & FALLOC_FL_PUNCH_HOLE) - return btrfs_punch_hole(inode, offset, len); - - /* - * Only trigger disk allocation, don't trigger qgroup reserve - * - * For qgroup space, it will be checked later. - */ - if (!(mode & FALLOC_FL_ZERO_RANGE)) { - ret = btrfs_alloc_data_chunk_ondemand(BTRFS_I(inode), - alloc_end - alloc_start); - if (ret < 0) - return ret; - } + return btrfs_punch_hole(file, offset, len); - inode_lock(inode); + btrfs_inode_lock(inode, BTRFS_ILOCK_MMAP); if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) { ret = inode_newsize_ok(inode, offset + len); @@ -3197,6 +3374,10 @@ static long btrfs_fallocate(struct file *file, int mode, goto out; } + ret = file_modified(file); + if (ret) + goto out; + /* * TODO: Move these two operations after we have checked * accurate reserved space, or fallocate can still fail but @@ -3205,7 +3386,7 @@ static long btrfs_fallocate(struct file *file, int mode, * But that's a minor problem and won't do much harm BTW. */ if (alloc_start > inode->i_size) { - ret = btrfs_cont_expand(inode, i_size_read(inode), + ret = btrfs_cont_expand(BTRFS_I(inode), i_size_read(inode), alloc_start); if (ret) goto out; @@ -3215,14 +3396,18 @@ static long btrfs_fallocate(struct file *file, int mode, * need to zero out the end of the block if i_size lands in the * middle of a block. */ - ret = btrfs_truncate_block(inode, inode->i_size, 0, 0); + ret = btrfs_truncate_block(BTRFS_I(inode), inode->i_size, 0, 0); if (ret) goto out; } /* - * wait for ordered IO before we have any locks. We'll loop again - * below with the locks held. + * We have locked the inode at the VFS level (in exclusive mode) and we + * have locked the i_mmap_lock lock (in exclusive mode). Now before + * locking the file range, flush all dealloc in the range and wait for + * all ordered extents in the range to complete. After this we can lock + * the file range and, due to the previous locking we did, we know there + * can't be more delalloc or ordered extents in the range. */ ret = btrfs_wait_ordered_range(inode, alloc_start, alloc_end - alloc_start); @@ -3231,42 +3416,15 @@ static long btrfs_fallocate(struct file *file, int mode, if (mode & FALLOC_FL_ZERO_RANGE) { ret = btrfs_zero_range(inode, offset, len, mode); - inode_unlock(inode); + btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP); return ret; } locked_end = alloc_end - 1; - while (1) { - struct btrfs_ordered_extent *ordered; + lock_extent(&BTRFS_I(inode)->io_tree, alloc_start, locked_end, + &cached_state); - /* the extent lock is ordered inside the running - * transaction - */ - lock_extent_bits(&BTRFS_I(inode)->io_tree, alloc_start, - locked_end, &cached_state); - ordered = btrfs_lookup_first_ordered_extent(inode, locked_end); - - if (ordered && - ordered->file_offset + ordered->num_bytes > alloc_start && - ordered->file_offset < alloc_end) { - btrfs_put_ordered_extent(ordered); - unlock_extent_cached(&BTRFS_I(inode)->io_tree, - alloc_start, locked_end, - &cached_state); - /* - * we can't wait on the range with the transaction - * running or with the extent lock held - */ - ret = btrfs_wait_ordered_range(inode, alloc_start, - alloc_end - alloc_start); - if (ret) - goto out; - } else { - if (ordered) - btrfs_put_ordered_extent(ordered); - break; - } - } + btrfs_assert_inode_range_clean(BTRFS_I(inode), alloc_start, locked_end); /* First, check if we exceed the qgroup limit */ INIT_LIST_HEAD(&reserve_list); @@ -3283,46 +3441,64 @@ static long btrfs_fallocate(struct file *file, int mode, if (em->block_start == EXTENT_MAP_HOLE || (cur_offset >= inode->i_size && !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) { - ret = add_falloc_range(&reserve_list, cur_offset, - last_byte - cur_offset); + const u64 range_len = last_byte - cur_offset; + + ret = add_falloc_range(&reserve_list, cur_offset, range_len); if (ret < 0) { free_extent_map(em); break; } - ret = btrfs_qgroup_reserve_data(inode, &data_reserved, - cur_offset, last_byte - cur_offset); + ret = btrfs_qgroup_reserve_data(BTRFS_I(inode), + &data_reserved, cur_offset, range_len); if (ret < 0) { - cur_offset = last_byte; free_extent_map(em); break; } - } else { - /* - * Do not need to reserve unwritten extent for this - * range, free reserved data space first, otherwise - * it'll result in false ENOSPC error. - */ - btrfs_free_reserved_data_space(inode, data_reserved, - cur_offset, last_byte - cur_offset); + qgroup_reserved += range_len; + data_space_needed += range_len; } free_extent_map(em); cur_offset = last_byte; } + if (!ret && data_space_needed > 0) { + /* + * We are safe to reserve space here as we can't have delalloc + * in the range, see above. + */ + ret = btrfs_alloc_data_chunk_ondemand(BTRFS_I(inode), + data_space_needed); + if (!ret) + data_space_reserved = data_space_needed; + } + /* * If ret is still 0, means we're OK to fallocate. * Or just cleanup the list and exit. */ list_for_each_entry_safe(range, tmp, &reserve_list, list) { - if (!ret) + if (!ret) { ret = btrfs_prealloc_file_range(inode, mode, range->start, range->len, i_blocksize(inode), offset + len, &alloc_hint); - else - btrfs_free_reserved_data_space(inode, - data_reserved, range->start, - range->len); + /* + * btrfs_prealloc_file_range() releases space even + * if it returns an error. + */ + data_space_reserved -= range->len; + qgroup_reserved -= range->len; + } else if (data_space_reserved > 0) { + btrfs_free_reserved_data_space(BTRFS_I(inode), + data_reserved, range->start, + range->len); + data_space_reserved -= range->len; + qgroup_reserved -= range->len; + } else if (qgroup_reserved > 0) { + btrfs_qgroup_free_data(BTRFS_I(inode), data_reserved, + range->start, range->len); + qgroup_reserved -= range->len; + } list_del(&range->list); kfree(range); } @@ -3335,35 +3511,290 @@ static long btrfs_fallocate(struct file *file, int mode, */ ret = btrfs_fallocate_update_isize(inode, actual_end, mode); out_unlock: - unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end, - &cached_state); + unlock_extent(&BTRFS_I(inode)->io_tree, alloc_start, locked_end, + &cached_state); out: - inode_unlock(inode); - /* Let go of our reservation. */ - if (ret != 0 && !(mode & FALLOC_FL_ZERO_RANGE)) - btrfs_free_reserved_data_space(inode, data_reserved, - cur_offset, alloc_end - cur_offset); + btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP); extent_changeset_free(data_reserved); return ret; } -static loff_t find_desired_extent(struct inode *inode, loff_t offset, +/* + * Helper for btrfs_find_delalloc_in_range(). Find a subrange in a given range + * that has unflushed and/or flushing delalloc. There might be other adjacent + * subranges after the one it found, so btrfs_find_delalloc_in_range() keeps + * looping while it gets adjacent subranges, and merging them together. + */ +static bool find_delalloc_subrange(struct btrfs_inode *inode, u64 start, u64 end, + u64 *delalloc_start_ret, u64 *delalloc_end_ret) +{ + const u64 len = end + 1 - start; + struct extent_map_tree *em_tree = &inode->extent_tree; + struct extent_map *em; + u64 em_end; + u64 delalloc_len; + + /* + * Search the io tree first for EXTENT_DELALLOC. If we find any, it + * means we have delalloc (dirty pages) for which writeback has not + * started yet. + */ + *delalloc_start_ret = start; + delalloc_len = count_range_bits(&inode->io_tree, delalloc_start_ret, end, + len, EXTENT_DELALLOC, 1); + /* + * If delalloc was found then *delalloc_start_ret has a sector size + * aligned value (rounded down). + */ + if (delalloc_len > 0) + *delalloc_end_ret = *delalloc_start_ret + delalloc_len - 1; + + /* + * Now also check if there's any extent map in the range that does not + * map to a hole or prealloc extent. We do this because: + * + * 1) When delalloc is flushed, the file range is locked, we clear the + * EXTENT_DELALLOC bit from the io tree and create an extent map for + * an allocated extent. So we might just have been called after + * delalloc is flushed and before the ordered extent completes and + * inserts the new file extent item in the subvolume's btree; + * + * 2) We may have an extent map created by flushing delalloc for a + * subrange that starts before the subrange we found marked with + * EXTENT_DELALLOC in the io tree. + */ + read_lock(&em_tree->lock); + em = lookup_extent_mapping(em_tree, start, len); + read_unlock(&em_tree->lock); + + /* extent_map_end() returns a non-inclusive end offset. */ + em_end = em ? extent_map_end(em) : 0; + + /* + * If we have a hole/prealloc extent map, check the next one if this one + * ends before our range's end. + */ + if (em && (em->block_start == EXTENT_MAP_HOLE || + test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) && em_end < end) { + struct extent_map *next_em; + + read_lock(&em_tree->lock); + next_em = lookup_extent_mapping(em_tree, em_end, len - em_end); + read_unlock(&em_tree->lock); + + free_extent_map(em); + em_end = next_em ? extent_map_end(next_em) : 0; + em = next_em; + } + + if (em && (em->block_start == EXTENT_MAP_HOLE || + test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) { + free_extent_map(em); + em = NULL; + } + + /* + * No extent map or one for a hole or prealloc extent. Use the delalloc + * range we found in the io tree if we have one. + */ + if (!em) + return (delalloc_len > 0); + + /* + * We don't have any range as EXTENT_DELALLOC in the io tree, so the + * extent map is the only subrange representing delalloc. + */ + if (delalloc_len == 0) { + *delalloc_start_ret = em->start; + *delalloc_end_ret = min(end, em_end - 1); + free_extent_map(em); + return true; + } + + /* + * The extent map represents a delalloc range that starts before the + * delalloc range we found in the io tree. + */ + if (em->start < *delalloc_start_ret) { + *delalloc_start_ret = em->start; + /* + * If the ranges are adjacent, return a combined range. + * Otherwise return the extent map's range. + */ + if (em_end < *delalloc_start_ret) + *delalloc_end_ret = min(end, em_end - 1); + + free_extent_map(em); + return true; + } + + /* + * The extent map starts after the delalloc range we found in the io + * tree. If it's adjacent, return a combined range, otherwise return + * the range found in the io tree. + */ + if (*delalloc_end_ret + 1 == em->start) + *delalloc_end_ret = min(end, em_end - 1); + + free_extent_map(em); + return true; +} + +/* + * Check if there's delalloc in a given range. + * + * @inode: The inode. + * @start: The start offset of the range. It does not need to be + * sector size aligned. + * @end: The end offset (inclusive value) of the search range. + * It does not need to be sector size aligned. + * @delalloc_start_ret: Output argument, set to the start offset of the + * subrange found with delalloc (may not be sector size + * aligned). + * @delalloc_end_ret: Output argument, set to he end offset (inclusive value) + * of the subrange found with delalloc. + * + * Returns true if a subrange with delalloc is found within the given range, and + * if so it sets @delalloc_start_ret and @delalloc_end_ret with the start and + * end offsets of the subrange. + */ +bool btrfs_find_delalloc_in_range(struct btrfs_inode *inode, u64 start, u64 end, + u64 *delalloc_start_ret, u64 *delalloc_end_ret) +{ + u64 cur_offset = round_down(start, inode->root->fs_info->sectorsize); + u64 prev_delalloc_end = 0; + bool ret = false; + + while (cur_offset < end) { + u64 delalloc_start; + u64 delalloc_end; + bool delalloc; + + delalloc = find_delalloc_subrange(inode, cur_offset, end, + &delalloc_start, + &delalloc_end); + if (!delalloc) + break; + + if (prev_delalloc_end == 0) { + /* First subrange found. */ + *delalloc_start_ret = max(delalloc_start, start); + *delalloc_end_ret = delalloc_end; + ret = true; + } else if (delalloc_start == prev_delalloc_end + 1) { + /* Subrange adjacent to the previous one, merge them. */ + *delalloc_end_ret = delalloc_end; + } else { + /* Subrange not adjacent to the previous one, exit. */ + break; + } + + prev_delalloc_end = delalloc_end; + cur_offset = delalloc_end + 1; + cond_resched(); + } + + return ret; +} + +/* + * Check if there's a hole or delalloc range in a range representing a hole (or + * prealloc extent) found in the inode's subvolume btree. + * + * @inode: The inode. + * @whence: Seek mode (SEEK_DATA or SEEK_HOLE). + * @start: Start offset of the hole region. It does not need to be sector + * size aligned. + * @end: End offset (inclusive value) of the hole region. It does not + * need to be sector size aligned. + * @start_ret: Return parameter, used to set the start of the subrange in the + * hole that matches the search criteria (seek mode), if such + * subrange is found (return value of the function is true). + * The value returned here may not be sector size aligned. + * + * Returns true if a subrange matching the given seek mode is found, and if one + * is found, it updates @start_ret with the start of the subrange. + */ +static bool find_desired_extent_in_hole(struct btrfs_inode *inode, int whence, + u64 start, u64 end, u64 *start_ret) +{ + u64 delalloc_start; + u64 delalloc_end; + bool delalloc; + + delalloc = btrfs_find_delalloc_in_range(inode, start, end, + &delalloc_start, &delalloc_end); + if (delalloc && whence == SEEK_DATA) { + *start_ret = delalloc_start; + return true; + } + + if (delalloc && whence == SEEK_HOLE) { + /* + * We found delalloc but it starts after out start offset. So we + * have a hole between our start offset and the delalloc start. + */ + if (start < delalloc_start) { + *start_ret = start; + return true; + } + /* + * Delalloc range starts at our start offset. + * If the delalloc range's length is smaller than our range, + * then it means we have a hole that starts where the delalloc + * subrange ends. + */ + if (delalloc_end < end) { + *start_ret = delalloc_end + 1; + return true; + } + + /* There's delalloc for the whole range. */ + return false; + } + + if (!delalloc && whence == SEEK_HOLE) { + *start_ret = start; + return true; + } + + /* + * No delalloc in the range and we are seeking for data. The caller has + * to iterate to the next extent item in the subvolume btree. + */ + return false; +} + +static loff_t find_desired_extent(struct btrfs_inode *inode, loff_t offset, int whence) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct extent_map *em = NULL; + struct btrfs_fs_info *fs_info = inode->root->fs_info; struct extent_state *cached_state = NULL; - loff_t i_size = inode->i_size; + const loff_t i_size = i_size_read(&inode->vfs_inode); + const u64 ino = btrfs_ino(inode); + struct btrfs_root *root = inode->root; + struct btrfs_path *path; + struct btrfs_key key; + u64 last_extent_end; u64 lockstart; u64 lockend; u64 start; - u64 len; - int ret = 0; + int ret; + bool found = false; if (i_size == 0 || offset >= i_size) return -ENXIO; /* + * Quick path. If the inode has no prealloc extents and its number of + * bytes used matches its i_size, then it can not have holes. + */ + if (whence == SEEK_HOLE && + !(inode->flags & BTRFS_INODE_PREALLOC) && + inode_get_bytes(&inode->vfs_inode) == i_size) + return i_size; + + /* * offset can be negative, in this case we start finding DATA/HOLE from * the very start of the file. */ @@ -3374,46 +3805,164 @@ static loff_t find_desired_extent(struct inode *inode, loff_t offset, if (lockend <= lockstart) lockend = lockstart + fs_info->sectorsize; lockend--; - len = lockend - lockstart + 1; - lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend, - &cached_state); + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + path->reada = READA_FORWARD; + + key.objectid = ino; + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = start; + + last_extent_end = lockstart; + + lock_extent(&inode->io_tree, lockstart, lockend, &cached_state); + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) { + goto out; + } else if (ret > 0 && path->slots[0] > 0) { + btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0] - 1); + if (key.objectid == ino && key.type == BTRFS_EXTENT_DATA_KEY) + path->slots[0]--; + } while (start < i_size) { - em = btrfs_get_extent_fiemap(BTRFS_I(inode), start, len); - if (IS_ERR(em)) { - ret = PTR_ERR(em); - em = NULL; - break; + struct extent_buffer *leaf = path->nodes[0]; + struct btrfs_file_extent_item *extent; + u64 extent_end; + + if (path->slots[0] >= btrfs_header_nritems(leaf)) { + ret = btrfs_next_leaf(root, path); + if (ret < 0) + goto out; + else if (ret > 0) + break; + + leaf = path->nodes[0]; } - if (whence == SEEK_HOLE && - (em->block_start == EXTENT_MAP_HOLE || - test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) - break; - else if (whence == SEEK_DATA && - (em->block_start != EXTENT_MAP_HOLE && - !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) + btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); + if (key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY) break; - start = em->start + em->len; - free_extent_map(em); - em = NULL; + extent_end = btrfs_file_extent_end(path); + + /* + * In the first iteration we may have a slot that points to an + * extent that ends before our start offset, so skip it. + */ + if (extent_end <= start) { + path->slots[0]++; + continue; + } + + /* We have an implicit hole, NO_HOLES feature is likely set. */ + if (last_extent_end < key.offset) { + u64 search_start = last_extent_end; + u64 found_start; + + /* + * First iteration, @start matches @offset and it's + * within the hole. + */ + if (start == offset) + search_start = offset; + + found = find_desired_extent_in_hole(inode, whence, + search_start, + key.offset - 1, + &found_start); + if (found) { + start = found_start; + break; + } + /* + * Didn't find data or a hole (due to delalloc) in the + * implicit hole range, so need to analyze the extent. + */ + } + + extent = btrfs_item_ptr(leaf, path->slots[0], + struct btrfs_file_extent_item); + + if (btrfs_file_extent_disk_bytenr(leaf, extent) == 0 || + btrfs_file_extent_type(leaf, extent) == + BTRFS_FILE_EXTENT_PREALLOC) { + /* + * Explicit hole or prealloc extent, search for delalloc. + * A prealloc extent is treated like a hole. + */ + u64 search_start = key.offset; + u64 found_start; + + /* + * First iteration, @start matches @offset and it's + * within the hole. + */ + if (start == offset) + search_start = offset; + + found = find_desired_extent_in_hole(inode, whence, + search_start, + extent_end - 1, + &found_start); + if (found) { + start = found_start; + break; + } + /* + * Didn't find data or a hole (due to delalloc) in the + * implicit hole range, so need to analyze the next + * extent item. + */ + } else { + /* + * Found a regular or inline extent. + * If we are seeking for data, adjust the start offset + * and stop, we're done. + */ + if (whence == SEEK_DATA) { + start = max_t(u64, key.offset, offset); + found = true; + break; + } + /* + * Else, we are seeking for a hole, check the next file + * extent item. + */ + } + + start = extent_end; + last_extent_end = extent_end; + path->slots[0]++; + if (fatal_signal_pending(current)) { + ret = -EINTR; + goto out; + } cond_resched(); } - free_extent_map(em); - unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend, - &cached_state); - if (ret) { - offset = ret; - } else { - if (whence == SEEK_DATA && start >= i_size) - offset = -ENXIO; - else - offset = min_t(loff_t, start, i_size); + + /* We have an implicit hole from the last extent found up to i_size. */ + if (!found && start < i_size) { + found = find_desired_extent_in_hole(inode, whence, start, + i_size - 1, &start); + if (!found) + start = i_size; } - return offset; +out: + unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state); + btrfs_free_path(path); + + if (ret < 0) + return ret; + + if (whence == SEEK_DATA && start >= i_size) + return -ENXIO; + + return min_t(loff_t, start, i_size); } static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int whence) @@ -3425,9 +3974,9 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int whence) return generic_file_llseek(file, offset, whence); case SEEK_DATA: case SEEK_HOLE: - inode_lock_shared(inode); - offset = find_desired_extent(inode, offset, whence); - inode_unlock_shared(inode); + btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED); + offset = find_desired_extent(BTRFS_I(inode), offset, whence); + btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); break; } @@ -3439,18 +3988,126 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int whence) static int btrfs_file_open(struct inode *inode, struct file *filp) { - filp->f_mode |= FMODE_NOWAIT; + int ret; + + filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC | FMODE_BUF_WASYNC; + + ret = fsverity_file_open(inode, filp); + if (ret) + return ret; return generic_file_open(inode, filp); } +static int check_direct_read(struct btrfs_fs_info *fs_info, + const struct iov_iter *iter, loff_t offset) +{ + int ret; + int i, seg; + + ret = check_direct_IO(fs_info, iter, offset); + if (ret < 0) + return ret; + + if (!iter_is_iovec(iter)) + return 0; + + for (seg = 0; seg < iter->nr_segs; seg++) + for (i = seg + 1; i < iter->nr_segs; i++) + if (iter->iov[seg].iov_base == iter->iov[i].iov_base) + return -EINVAL; + return 0; +} + +static ssize_t btrfs_direct_read(struct kiocb *iocb, struct iov_iter *to) +{ + struct inode *inode = file_inode(iocb->ki_filp); + size_t prev_left = 0; + ssize_t read = 0; + ssize_t ret; + + if (fsverity_active(inode)) + return 0; + + if (check_direct_read(btrfs_sb(inode->i_sb), to, iocb->ki_pos)) + return 0; + + btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED); +again: + /* + * This is similar to what we do for direct IO writes, see the comment + * at btrfs_direct_write(), but we also disable page faults in addition + * to disabling them only at the iov_iter level. This is because when + * reading from a hole or prealloc extent, iomap calls iov_iter_zero(), + * which can still trigger page fault ins despite having set ->nofault + * to true of our 'to' iov_iter. + * + * The difference to direct IO writes is that we deadlock when trying + * to lock the extent range in the inode's tree during he page reads + * triggered by the fault in (while for writes it is due to waiting for + * our own ordered extent). This is because for direct IO reads, + * btrfs_dio_iomap_begin() returns with the extent range locked, which + * is only unlocked in the endio callback (end_bio_extent_readpage()). + */ + pagefault_disable(); + to->nofault = true; + ret = btrfs_dio_read(iocb, to, read); + to->nofault = false; + pagefault_enable(); + + /* No increment (+=) because iomap returns a cumulative value. */ + if (ret > 0) + read = ret; + + if (iov_iter_count(to) > 0 && (ret == -EFAULT || ret > 0)) { + const size_t left = iov_iter_count(to); + + if (left == prev_left) { + /* + * We didn't make any progress since the last attempt, + * fallback to a buffered read for the remainder of the + * range. This is just to avoid any possibility of looping + * for too long. + */ + ret = read; + } else { + /* + * We made some progress since the last retry or this is + * the first time we are retrying. Fault in as many pages + * as possible and retry. + */ + fault_in_iov_iter_writeable(to, left); + prev_left = left; + goto again; + } + } + btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); + return ret < 0 ? ret : read; +} + +static ssize_t btrfs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) +{ + ssize_t ret = 0; + + if (iocb->ki_flags & IOCB_DIRECT) { + ret = btrfs_direct_read(iocb, to); + if (ret < 0 || !iov_iter_count(to) || + iocb->ki_pos >= i_size_read(file_inode(iocb->ki_filp))) + return ret; + } + + return filemap_read(iocb, to, ret); +} + const struct file_operations btrfs_file_operations = { .llseek = btrfs_file_llseek, - .read_iter = generic_file_read_iter, + .read_iter = btrfs_file_read_iter, .splice_read = generic_file_splice_read, .write_iter = btrfs_file_write_iter, + .splice_write = iter_file_splice_write, .mmap = btrfs_file_mmap, .open = btrfs_file_open, .release = btrfs_release_file, + .get_unmapped_area = thp_get_unmapped_area, .fsync = btrfs_sync_file, .fallocate = btrfs_fallocate, .unlocked_ioctl = btrfs_ioctl, |